All-Model Benchmarks Ranking

Multi-dimensional benchmark ranking for every model: Artificial Analysis composite indexes plus OpenRouter in-house eval accuracy for reasoning, tool calling, and search, with sources and eval dates.

OpenRouter reasoning evals such as GPQA Diamond (accuracy × 100).

Google: Gemini 4 Argon

google/gemini-4-argon-20261013

Sources: openrouter-benchmarks · Last eval Oct 14, 2026

gpqa-diamond: 96.5
Best

Google: Gemini 3.8 Flash

google/gemini-3.8-flash-20260902

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 95.6

OpenAI: GPT-6 Astra Pro

openai/gpt-6-astra-pro-20260903

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 95.5

Fugu Ultra

sakana/fugu-ultra

Sources: openrouter-benchmarks · Last eval Sep 15, 2026

gpqa-diamond: 94.6

Google: Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview-20260219

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 94.5

OpenAI: GPT-6 Astra

openai/gpt-6-astra-20260903

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 94.4

OpenAI: GPT-6.1 Sol

openai/gpt-6.1-sol-20260929

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 94.4

Google: Gemini 3.7 Flash

google/gemini-3.7-flash-20260813

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 93.9

OpenAI: GPT-5.6 Sol Pro

openai/gpt-5.6-sol-pro-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 93.9

OpenAI: GPT-5.5

openai/gpt-5.5-20260423

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 93.7

Fugu Ultra V2

sakana/fugu-ultra-v2

Sources: openrouter-benchmarks · Last eval Sep 15, 2026

gpqa-diamond: 93.3

TypeSafe: Jev Router

typesafe/jev-router

Sources: openrouter-benchmarks · Last eval Oct 9, 2026

gpqa-diamond: 93.3

SpaceXAI: Grok 4.6

x-ai/grok-4.6-20260810

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 92.8

Google: Gemini 3.5 Flash

google/gemini-3.5-flash-20260519

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 92.6

Google: Gemini 3.6 Flash

google/gemini-3.6-flash-20260721

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 92.6

Anthropic: Claude Sonnet 5.5

anthropic/claude-sonnet-5.5-20260928

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 92.4

Pareto

unbiased/pareto

Sources: openrouter-benchmarks · Last eval Sep 29, 2026

gpqa-diamond: 92.4

OpenAI: GPT-5.6 Sol

openai/gpt-5.6-sol-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 92.1

MoonshotAI: Kimi K3

moonshotai/kimi-k3-20260715

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 92

OpenAI: GPT-6 Sol

openai/gpt-6-sol-20260922

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 91.9

Qwen: Qwen3.7 Max

qwen/qwen3.7-max-20260520

Sources: openrouter-benchmarks · Last eval Sep 27, 2026

gpqa-diamond: 90.9

GLM 5.3 Flash

z-ai/glm-5.3-flash

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 90.9

NVIDIA: Switchyard

nvidia/switchyard

Sources: openrouter-benchmarks · Last eval Sep 30, 2026

gpqa-diamond: 90.7

MiniMax: MiniMax M3

minimax/minimax-m3-20260531

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 90.5

OpenAI: GPT-5.4

openai/gpt-5.4-20260305

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 90.3

Anthropic: Claude Opus 5.5

anthropic/claude-opus-5.5-20260921

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 90.2

DeepSeek: DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-20260813

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 90.1

OpenAI: GPT-5.6 Luna Pro

openai/gpt-5.6-luna-pro-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 90

Anthropic: Claude Fable 5.1

anthropic/claude-fable-5.1-20260831

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 89.9

GPT-6-Luna

openai/gpt-6-luna

Sources: openrouter-benchmarks · Last eval Oct 8, 2026

gpqa-diamond: 89.8

Anthropic: Claude Opus 4.8

anthropic/claude-4.8-opus-20260528

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 89.7

Tencent: Hy4 preview

tencent/hy4-preview-20260827

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 89.7

Anthropic: Claude Opus 4.7

anthropic/claude-4.7-opus-20260416

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 89.4

Amazon: Nova Micro 1.0

amazon/nova-micro-v1

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 89

DeepSeek: DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash-20260910

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 88.8

OpenAI: GPT-5.6 Terra

openai/gpt-5.6-terra-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 88.8

Qwen: Qwen3.8 Flash

qwen/qwen3.8-flash-20260826

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 88.6

Fugu Max

sakana/fugu-max

Sources: openrouter-benchmarks · Last eval Sep 15, 2026

gpqa-diamond: 88.6

Xiaomi: MiMo-V2.6-Pro

xiaomi/mimo-v2.6-pro-20260921

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 88.5

Google: Gemini 3 Flash Preview

google/gemini-3-flash-preview-20251217

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 88.4

OpenAI: GPT-6 Luna Pro

openai/gpt-6-luna-pro-20260922

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 88.4

DeepSeek: DeepSeek V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp-20260821

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 88

Auto Router

openrouter/auto

Sources: openrouter-benchmarks · Last eval Sep 29, 2026

gpqa-diamond: 88

Deepseek V4.1 Flash

deepseek/deepseek-v4.1-flash

Sources: openrouter-benchmarks · Last eval Oct 8, 2026

gpqa-diamond: 87.9

OpenAI: GPT-5.2

openai/gpt-5.2-20251211

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 87.9

OpenAI: GPT-5.6 Luna

openai/gpt-5.6-luna-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 87.9

Qwen: Qwen3.7 Plus

qwen/qwen3.7-plus-20260602

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 87.9

Mimo V2.6 Pro

xiaomi/mimo-v2.6-pro

Sources: openrouter-benchmarks · Last eval Oct 8, 2026

gpqa-diamond: 87.9

Anthropic: Claude Opus 5

anthropic/claude-opus-5-20260723

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 87.6

OpenAI: GPT-6 Luna

openai/gpt-6-luna-20260922

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 87.4

MoonshotAI: Kimi K2 Thinking

moonshotai/kimi-k2-thinking-20251106

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 87.3

Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b-20260812

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86.9

Thinking Machines: Inkling Small

thinkingmachines/inkling-small-20260730

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 86.6

DeepSeek: DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro-20260423

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86.4

OpenAI: GPT-5.1

openai/gpt-5.1-20251113

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 86.4

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-20260731

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 86.3

MiniMax: MiniMax M2.1

minimax/minimax-m2.1

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 86.3

Anthropic: Claude Opus 4.6

anthropic/claude-4.6-opus-20260205

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86.2

Anthropic: Claude Haiku 5.5

anthropic/claude-haiku-5.5-20261007

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86.2

Anthropic: Claude Opus 4.5

anthropic/claude-4.5-opus-20251124

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86.1

MoonshotAI: Kimi K2.7 Code

moonshotai/kimi-k2.7-code-20260612

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 86

Anthropic: Claude Fable 5

anthropic/claude-5-fable-20260609

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 85.8

OpenAI: GPT-5

openai/gpt-5-2025-08-07

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 85.7

DeepSeek: DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-20260423

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 85.5

Z.ai: GLM 5.3

z-ai/glm-5.3-20260816

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 85.2

Z.ai: GLM 5.3 Flash

z-ai/glm-5.3-flash-20260826

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 85

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6-20260420

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84.9

inclusionAI: Ling 3.0 Flash VL

inclusionai/ling-3.0-flash-vl-20260910

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 84.8

Z.ai: GLM 5.2

z-ai/glm-5.2-20260616

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84.8

Qwen: Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b-20260216

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84.6

MiniMax: MiniMax M2.7

minimax/minimax-m2.7-20260318

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84.3

MoonshotAI: Kimi K2.5

moonshotai/kimi-k2.5-0127

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84.3

Google: Gemini 3.5 Flash Lite

google/gemini-3.5-flash-lite-20260721

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 84.1

Anthropic: Claude Sonnet 5

anthropic/claude-sonnet-5-20260630

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 84

OpenAI: GPT-5.4 Mini

openai/gpt-5.4-mini-20260317

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 83.5

Thinking Machines: Inkling

thinkingmachines/inkling-20260715

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 83.4

Qwen: Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b-20260224

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 83.3

MiniMax: MiniMax M2.5

minimax/minimax-m2.5-20260211

Sources: openrouter-benchmarks · Last eval Aug 29, 2026

gpqa-diamond: 82.8

Xiaomi: MiMo-V2.5-Pro

xiaomi/mimo-v2.5-pro-20260422

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 82.3

GLM 5.3

z-ai/glm-5.3

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 82.3

DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 82.1

Anthropic: Claude Sonnet 4.5

anthropic/claude-4.5-sonnet-20250929

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 82

Qwen: Qwen3.6 27B

qwen/qwen3.6-27b-20260422

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 81.9

Qwen: Qwen3.8 27B

qwen/qwen3.8-27b-20260814

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 81.9

Z.ai: GLM 4.7

z-ai/glm-4.7-20251222

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 81.7

Google: Gemini 3.1 Flash Lite

google/gemini-3.1-flash-lite-20260507

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 81.6

Google: Gemma 4 31B

google/gemma-4-31b-it-20260402

Sources: openrouter-benchmarks · Last eval Oct 12, 2026

gpqa-diamond: 81.5

Z.ai: GLM 5.1

z-ai/glm-5.1-20260406

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 81.5

Google: Gemini 2.5 Pro

google/gemini-2.5-pro

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 81.3

inclusionAI: Ling 3.1 Flash

inclusionai/ling-3.1-flash-20261002

Sources: openrouter-benchmarks · Last eval Oct 14, 2026

gpqa-diamond: 81.3

NVIDIA: Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b-20260604

Sources: openrouter-benchmarks · Last eval Aug 4, 2026

gpqa-diamond: 81.2

DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2-20251201

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 81

OpenAI: GPT-5 Mini

openai/gpt-5-mini-2025-08-07

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 80.8

Meta: Muse Glimmer 30B

meta/muse-glimmer-30b-20260810

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 80.6

OpenAI: GPT-5.3 Chat

openai/gpt-5.3-chat-20260303

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 80.5

Qwen: Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b-20260224

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 80.1

OpenAI: GPT-5.2 Chat

openai/gpt-5.2-chat-20251211

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 79.8

Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b-20260415

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 78.8

Qwen: Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Sources: openrouter-benchmarks · Last eval Aug 22, 2026

gpqa-diamond: 77.8

OpenAI: GPT-5.4 Nano

openai/gpt-5.4-nano-20260317

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 77.7

Qwen: Qwen3.5-9B

qwen/qwen3.5-9b-20260310

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 77.7

DeepSeek: R1 0528

deepseek/deepseek-r1-0528

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 77.4

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

Sources: openrouter-benchmarks · Last eval Aug 29, 2026

gpqa-diamond: 77.3

Anthropic: Claude Sonnet 4

anthropic/claude-4-sonnet-20250522

Sources: openrouter-benchmarks · Last eval Sep 1, 2026

gpqa-diamond: 76.7

StepFun: Step 3.7 Flash

stepfun/step-3.7-flash-20260528

Sources: openrouter-benchmarks · Last eval Jul 18, 2026

gpqa-diamond: 76.6

Xiaomi: MiMo-V2.5

xiaomi/mimo-v2.5-20260422

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 76.1

Mistral: Mistral Small 4

mistralai/mistral-small-2603

Sources: openrouter-benchmarks · Last eval Sep 1, 2026

gpqa-diamond: 75.8

Z.ai: GLM 5

z-ai/glm-5-20260211

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 75.4

Xiaomi: MiMo-V2.6-Flash

xiaomi/mimo-v2.6-flash-20260921

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 75.1

inclusionAI: Ling 3.0 Flash

inclusionai/ling-3.0-flash-20260723

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 74.9

Z.ai: GLM 4.6

z-ai/glm-4.6

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 74.9

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 74.7

Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next-2025-02-03

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 74.6

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-07-25

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 73

Anthropic: Claude Haiku 4.5

anthropic/claude-4.5-haiku-20251001

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 72.8

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 72.7

Google: Gemini 2.5 Flash

google/gemini-2.5-flash

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 72.6

Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it-20260403

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 71.8

Qwen: Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct-2509

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 71.2

OpenAI: GPT-5 Nano

openai/gpt-5-nano-2025-08-07

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 70.5

NVIDIA: Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning-20260807

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 69.8

DeepSeek: DeepSeek V3.1

deepseek/deepseek-chat-v3.1

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 69.6

Qwen: Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 69.3

Gemma 4 26B A4B IT (free)

google/gemma-4-26b-a4b-it-20260403:free

Sources: openrouter-benchmarks · Last eval Aug 4, 2026

gpqa-diamond: 68.5

Z.ai: GLM 4.6V

z-ai/glm-4.6-20251208

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 66.8

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick-17b-128e-instruct

Sources: openrouter-benchmarks · Last eval Aug 29, 2026

gpqa-diamond: 66.3

IBM: Granite 4.2 8B

ibm-granite/granite-4.2-8b-20260831

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 65.7

Anthropic: Claude Sonnet 4.6

anthropic/claude-4.6-sonnet-20260217

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 65.5

OpenAI: GPT-4.1 Mini

openai/gpt-4.1-mini-2025-04-14

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 64.9

OpenAI: GPT-4.1

openai/gpt-4.1-2025-04-14

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 64.6

Qwen: Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 64.6

Qwen: Qwen3 30B A3B Instruct 2507

qwen/qwen3-30b-a3b-instruct-2507

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 64.3

OpenAI: gpt-oss-20b

openai/gpt-oss-20b

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 63.8

NVIDIA: Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 62.9

Z.ai: GLM 4.5 Air

z-ai/glm-4.5-air

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 62.3

DeepSeek: DeepSeek V3

deepseek/deepseek-chat-v3

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 62.1

Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b-04-28

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 62.1

Qwen: Qwen3 32B

qwen/qwen3-32b-04-28

Sources: openrouter-benchmarks · Last eval Aug 29, 2026

gpqa-diamond: 60.8

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder-480b-a35b-07-25

Sources: openrouter-benchmarks · Last eval Oct 3, 2026

gpqa-diamond: 60.5

Qwen: Qwen3 14B

qwen/qwen3-14b-04-28

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 59.2

Google: Gemini 2.5 Flash Lite

google/gemini-2.5-flash-lite

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 54.9

Z.ai: GLM 4.7 Flash

z-ai/glm-4.7-flash-20260119

Sources: openrouter-benchmarks · Last eval Aug 30, 2026

gpqa-diamond: 52.8

OpenAI: GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 52

Qwen: Qwen3 Coder 30B A3B Instruct

qwen/qwen3-coder-30b-a3b-instruct

Sources: openrouter-benchmarks · Last eval Aug 15, 2026

gpqa-diamond: 52

Qwen: Qwen3 VL 8B Instruct

qwen/qwen3-vl-8b-instruct

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 51.3

DeepSeek: DeepSeek V3 0324

deepseek/deepseek-chat-v3-0324

Sources: openrouter-benchmarks · Last eval Aug 29, 2026

gpqa-diamond: 50.8

OpenAI: GPT-4o (2024-05-13)

openai/gpt-4o-2024-05-13

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 50.7

OpenAI: GPT-4o

openai/gpt-4o

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 50.6

inclusionAI: Ling 3.0 Flash Fin

inclusionai/ling-3.0-flash-fin-20260827

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 50.5

OpenAI: GPT-4.1 Nano

openai/gpt-4.1-nano-2025-04-14

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 50

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 47.3

Qwen2.5 72B Instruct

qwen/qwen-2.5-72b-instruct

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 46

Qwen: Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct

Sources: openrouter-benchmarks · Last eval Sep 1, 2026

gpqa-diamond: 44.4

OpenAI: GPT-4o-mini

openai/gpt-4o-mini

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 43.2

Tencent: Hy-MT2-30B-A3B

tencent/hy-mt2-30b-a3b-20260521

Sources: openrouter-benchmarks · Last eval Sep 24, 2026

gpqa-diamond: 38.9

Google: Gemma 3 12B

google/gemma-3-12b-it

Sources: openrouter-benchmarks · Last eval Oct 8, 2026

gpqa-diamond: 37.9

Mistral: Mistral Nemo

mistralai/mistral-nemo

Sources: openrouter-benchmarks · Last eval Jul 18, 2026

gpqa-diamond: 33.8

Qwen: Qwen2.5 7B Instruct

qwen/qwen-2.5-7b-instruct

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 32.8

Meta: Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

Sources: openrouter-benchmarks · Last eval Oct 10, 2026

gpqa-diamond: 28.5

Sao10K: Llama 3 8B Lunaris

sao10k/l3-lunaris-8b

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 27.3

Google: Gemma 3 4B

google/gemma-3-4b-it

Sources: openrouter-benchmarks · Last eval Oct 15, 2026

gpqa-diamond: 27.1

Meta: Llama 3.2 3B Instruct

meta-llama/llama-3.2-3b-instruct

Sources: openrouter-benchmarks · Last eval Aug 1, 2026

gpqa-diamond: 11.6

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

google/gemini-3.1-flash-lite-image-20260630

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: 10.3

anthropic/claude-opus-5

Sources: openrouter-benchmarks · Last eval Aug 14, 2026

gpqa-diamond: —

ByteDance Seed: Seed 1.6

bytedance-seed/seed-1.6-20250625

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

ByteDance Seed: Seed-2.0-Lite

bytedance-seed/seed-2.0-lite-20260309

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

ByteDance Seed: Seed-2.0-Mini

bytedance-seed/seed-2.0-mini-20260224

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

deepseek/deepseek-v4-flash-0731

Sources: openrouter-benchmarks · Last eval Aug 11, 2026

gpqa-diamond: —

Google: Gemini 3.1 Flash Lite Preview

google/gemini-3.1-flash-lite-preview-20260303

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Google: Gemini 3.1 Pro Preview Custom Tools

google/gemini-3.1-pro-preview-customtools-20260219

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Meta: Muse Spark 1.1

meta/muse-spark-1.1-20260709

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Meta: Muse Spark 1.2

meta/muse-spark-1.2-20260805

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Meta: Muse Spark 1.3

meta/muse-spark-1.3-20260902

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Meta: Muse Wonder

meta/muse-wonder-20261012

Sources: openrouter-benchmarks · Last eval Oct 12, 2026

gpqa-diamond: —

OpenAI: GPT-5.3-Codex

openai/gpt-5.3-codex-20260224

Sources: openrouter-benchmarks · Last eval Oct 2, 2026

gpqa-diamond: —

openai/gpt-5.6-luna

Sources: openrouter-benchmarks · Last eval Aug 11, 2026

gpqa-diamond: —

openai/gpt-5.6-sol

Sources: openrouter-benchmarks · Last eval Aug 11, 2026

gpqa-diamond: —

Perceptron: Perceptron Mk1

perceptron/perceptron-mk1-20260512

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Perceptron: Perceptron Mk1.5

perceptron/perceptron-mk1.5-20260925

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.5-Flash

qwen/qwen3.5-flash-20260224

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-20260216

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.5 Plus 2026-04-20

qwen/qwen3.5-plus-20260420

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.6 Flash

qwen/qwen3.6-flash

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.6 Plus

qwen/qwen3.6-plus-04-02

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.7 Flash

qwen/qwen3.7-flash-20260727

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.8 Max (0803)

qwen/qwen3.8-max-20260803

Sources: openrouter-benchmarks · Last eval Sep 1, 2026

gpqa-diamond: —

Qwen: Qwen3.8 Max (0902)

qwen/qwen3.8-max-20260902

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Qwen: Qwen3.8 Omni Flash

qwen/qwen3.8-omni-flash-20260918

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Reka Edge

rekaai/reka-edge-2603

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Xiaomi: MiMo-V2.6-Pro-UltraSpeed

xiaomi/mimo-v2.6-pro-ultraspeed-20260921

Sources: openrouter-benchmarks · Last eval Sep 21, 2026

gpqa-diamond: —

Xiaomi: MiMo-X-Flash Preview

xiaomi/mimo-x-flash-preview-20260914

Sources: openrouter-benchmarks · Last eval Sep 14, 2026

gpqa-diamond: —

Xiaomi: MiMo-X-Pro Preview

xiaomi/mimo-x-pro-preview-20260914

Sources: openrouter-benchmarks · Last eval Sep 14, 2026

gpqa-diamond: —

Z.ai: GLM 5V Turbo

z-ai/glm-5v-turbo-20260401

Sources: openrouter-benchmarks · Last eval Oct 1, 2026

gpqa-diamond: —

Model
Google: Gemini 4 Argon google/gemini-4-argon-20261013 Sources: openrouter-benchmarks · Last eval Oct 14, 2026	96.5 Best
Google: Gemini 3.8 Flash google/gemini-3.8-flash-20260902 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	95.6
OpenAI: GPT-6 Astra Pro openai/gpt-6-astra-pro-20260903 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	95.5
Fugu Ultra sakana/fugu-ultra Sources: openrouter-benchmarks · Last eval Sep 15, 2026	94.6
Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview-20260219 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	94.5
OpenAI: GPT-6 Astra openai/gpt-6-astra-20260903 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	94.4
OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol-20260929 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	94.4
Google: Gemini 3.7 Flash google/gemini-3.7-flash-20260813 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	93.9
OpenAI: GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	93.9
OpenAI: GPT-5.5 openai/gpt-5.5-20260423 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	93.7
Fugu Ultra V2 sakana/fugu-ultra-v2 Sources: openrouter-benchmarks · Last eval Sep 15, 2026	93.3
TypeSafe: Jev Router typesafe/jev-router Sources: openrouter-benchmarks · Last eval Oct 9, 2026	93.3
SpaceXAI: Grok 4.6 x-ai/grok-4.6-20260810 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	92.8
Google: Gemini 3.5 Flash google/gemini-3.5-flash-20260519 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	92.6
Google: Gemini 3.6 Flash google/gemini-3.6-flash-20260721 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	92.6
Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5-20260928 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	92.4
Pareto unbiased/pareto Sources: openrouter-benchmarks · Last eval Sep 29, 2026	92.4
OpenAI: GPT-5.6 Sol openai/gpt-5.6-sol-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	92.1
MoonshotAI: Kimi K3 moonshotai/kimi-k3-20260715 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	92
OpenAI: GPT-6 Sol openai/gpt-6-sol-20260922 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	91.9
Qwen: Qwen3.7 Max qwen/qwen3.7-max-20260520 Sources: openrouter-benchmarks · Last eval Sep 27, 2026	90.9
GLM 5.3 Flash z-ai/glm-5.3-flash Sources: openrouter-benchmarks · Last eval Oct 1, 2026	90.9
NVIDIA: Switchyard nvidia/switchyard Sources: openrouter-benchmarks · Last eval Sep 30, 2026	90.7
MiniMax: MiniMax M3 minimax/minimax-m3-20260531 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	90.5
OpenAI: GPT-5.4 openai/gpt-5.4-20260305 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	90.3
Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5-20260921 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	90.2
DeepSeek: DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-20260813 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	90.1
OpenAI: GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	90
Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1-20260831 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	89.9
GPT-6-Luna openai/gpt-6-luna Sources: openrouter-benchmarks · Last eval Oct 8, 2026	89.8
Anthropic: Claude Opus 4.8 anthropic/claude-4.8-opus-20260528 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	89.7
Tencent: Hy4 preview tencent/hy4-preview-20260827 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	89.7
Anthropic: Claude Opus 4.7 anthropic/claude-4.7-opus-20260416 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	89.4
Amazon: Nova Micro 1.0 amazon/nova-micro-v1 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	89
DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash-20260910 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	88.8
OpenAI: GPT-5.6 Terra openai/gpt-5.6-terra-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	88.8
Qwen: Qwen3.8 Flash qwen/qwen3.8-flash-20260826 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	88.6
Fugu Max sakana/fugu-max Sources: openrouter-benchmarks · Last eval Sep 15, 2026	88.6
Xiaomi: MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro-20260921 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	88.5
Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	88.4
OpenAI: GPT-6 Luna Pro openai/gpt-6-luna-pro-20260922 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	88.4
DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp-20260821 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	88
Auto Router openrouter/auto Sources: openrouter-benchmarks · Last eval Sep 29, 2026	88
Deepseek V4.1 Flash deepseek/deepseek-v4.1-flash Sources: openrouter-benchmarks · Last eval Oct 8, 2026	87.9
OpenAI: GPT-5.2 openai/gpt-5.2-20251211 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	87.9
OpenAI: GPT-5.6 Luna openai/gpt-5.6-luna-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	87.9
Qwen: Qwen3.7 Plus qwen/qwen3.7-plus-20260602 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	87.9
Mimo V2.6 Pro xiaomi/mimo-v2.6-pro Sources: openrouter-benchmarks · Last eval Oct 8, 2026	87.9
Anthropic: Claude Opus 5 anthropic/claude-opus-5-20260723 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	87.6
OpenAI: GPT-6 Luna openai/gpt-6-luna-20260922 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	87.4
MoonshotAI: Kimi K2 Thinking moonshotai/kimi-k2-thinking-20251106 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	87.3
Qwen: Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b-20260812 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86.9
Thinking Machines: Inkling Small thinkingmachines/inkling-small-20260730 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	86.6
DeepSeek: DeepSeek V4 Pro 0423 deepseek/deepseek-v4-pro-20260423 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86.4
OpenAI: GPT-5.1 openai/gpt-5.1-20251113 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	86.4
DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-20260731 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	86.3
MiniMax: MiniMax M2.1 minimax/minimax-m2.1 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	86.3
Anthropic: Claude Opus 4.6 anthropic/claude-4.6-opus-20260205 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86.2
Anthropic: Claude Haiku 5.5 anthropic/claude-haiku-5.5-20261007 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86.2
Anthropic: Claude Opus 4.5 anthropic/claude-4.5-opus-20251124 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86.1
MoonshotAI: Kimi K2.7 Code moonshotai/kimi-k2.7-code-20260612 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	86
Anthropic: Claude Fable 5 anthropic/claude-5-fable-20260609 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	85.8
OpenAI: GPT-5 openai/gpt-5-2025-08-07 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	85.7
DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash-20260423 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	85.5
Z.ai: GLM 5.3 z-ai/glm-5.3-20260816 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	85.2
Z.ai: GLM 5.3 Flash z-ai/glm-5.3-flash-20260826 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	85
MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6-20260420 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84.9
inclusionAI: Ling 3.0 Flash VL inclusionai/ling-3.0-flash-vl-20260910 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	84.8
Z.ai: GLM 5.2 z-ai/glm-5.2-20260616 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84.8
Qwen: Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b-20260216 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84.6
MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84.3
MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5-0127 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84.3
Google: Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite-20260721 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	84.1
Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5-20260630 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	84
OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini-20260317 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	83.5
Thinking Machines: Inkling thinkingmachines/inkling-20260715 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	83.4
Qwen: Qwen3.5-122B-A10B qwen/qwen3.5-122b-a10b-20260224 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	83.3
MiniMax: MiniMax M2.5 minimax/minimax-m2.5-20260211 Sources: openrouter-benchmarks · Last eval Aug 29, 2026	82.8
Xiaomi: MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro-20260422 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	82.3
GLM 5.3 z-ai/glm-5.3 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	82.3
DeepSeek: DeepSeek V3.2 Exp deepseek/deepseek-v3.2-exp Sources: openrouter-benchmarks · Last eval Aug 1, 2026	82.1
Anthropic: Claude Sonnet 4.5 anthropic/claude-4.5-sonnet-20250929 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	82
Qwen: Qwen3.6 27B qwen/qwen3.6-27b-20260422 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	81.9
Qwen: Qwen3.8 27B qwen/qwen3.8-27b-20260814 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	81.9
Z.ai: GLM 4.7 z-ai/glm-4.7-20251222 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	81.7
Google: Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite-20260507 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	81.6
Google: Gemma 4 31B google/gemma-4-31b-it-20260402 Sources: openrouter-benchmarks · Last eval Oct 12, 2026	81.5
Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	81.5
Google: Gemini 2.5 Pro google/gemini-2.5-pro Sources: openrouter-benchmarks · Last eval Oct 1, 2026	81.3
inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash-20261002 Sources: openrouter-benchmarks · Last eval Oct 14, 2026	81.3
NVIDIA: Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b-20260604 Sources: openrouter-benchmarks · Last eval Aug 4, 2026	81.2
DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	81
OpenAI: GPT-5 Mini openai/gpt-5-mini-2025-08-07 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	80.8
Meta: Muse Glimmer 30B meta/muse-glimmer-30b-20260810 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	80.6
OpenAI: GPT-5.3 Chat openai/gpt-5.3-chat-20260303 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	80.5
Qwen: Qwen3.5-35B-A3B qwen/qwen3.5-35b-a3b-20260224 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	80.1
OpenAI: GPT-5.2 Chat openai/gpt-5.2-chat-20251211 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	79.8
Qwen: Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b-20260415 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	78.8
Qwen: Qwen3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 Sources: openrouter-benchmarks · Last eval Aug 22, 2026	77.8
OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano-20260317 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	77.7
Qwen: Qwen3.5-9B qwen/qwen3.5-9b-20260310 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	77.7
DeepSeek: R1 0528 deepseek/deepseek-r1-0528 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	77.4
DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus Sources: openrouter-benchmarks · Last eval Aug 29, 2026	77.3
Anthropic: Claude Sonnet 4 anthropic/claude-4-sonnet-20250522 Sources: openrouter-benchmarks · Last eval Sep 1, 2026	76.7
StepFun: Step 3.7 Flash stepfun/step-3.7-flash-20260528 Sources: openrouter-benchmarks · Last eval Jul 18, 2026	76.6
Xiaomi: MiMo-V2.5 xiaomi/mimo-v2.5-20260422 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	76.1
Mistral: Mistral Small 4 mistralai/mistral-small-2603 Sources: openrouter-benchmarks · Last eval Sep 1, 2026	75.8
Z.ai: GLM 5 z-ai/glm-5-20260211 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	75.4
Xiaomi: MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash-20260921 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	75.1
inclusionAI: Ling 3.0 Flash inclusionai/ling-3.0-flash-20260723 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	74.9
Z.ai: GLM 4.6 z-ai/glm-4.6 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	74.9
MoonshotAI: Kimi K2 0905 moonshotai/kimi-k2-0905 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	74.7
Qwen: Qwen3 Coder Next qwen/qwen3-coder-next-2025-02-03 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	74.6
Qwen: Qwen3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-07-25 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	73
Anthropic: Claude Haiku 4.5 anthropic/claude-4.5-haiku-20251001 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	72.8
OpenAI: gpt-oss-120b openai/gpt-oss-120b Sources: openrouter-benchmarks · Last eval Oct 10, 2026	72.7
Google: Gemini 2.5 Flash google/gemini-2.5-flash Sources: openrouter-benchmarks · Last eval Oct 1, 2026	72.6
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it-20260403 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	71.8
Qwen: Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct-2509 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	71.2
OpenAI: GPT-5 Nano openai/gpt-5-nano-2025-08-07 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	70.5
NVIDIA: Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning-20260807 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	69.8
DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	69.6
Qwen: Qwen3 VL 235B A22B Instruct qwen/qwen3-vl-235b-a22b-instruct Sources: openrouter-benchmarks · Last eval Oct 3, 2026	69.3
Gemma 4 26B A4B IT (free) google/gemma-4-26b-a4b-it-20260403:free Sources: openrouter-benchmarks · Last eval Aug 4, 2026	68.5
Z.ai: GLM 4.6V z-ai/glm-4.6-20251208 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	66.8
Meta: Llama 4 Maverick meta-llama/llama-4-maverick-17b-128e-instruct Sources: openrouter-benchmarks · Last eval Aug 29, 2026	66.3
IBM: Granite 4.2 8B ibm-granite/granite-4.2-8b-20260831 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	65.7
Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 Sources: openrouter-benchmarks · Last eval Oct 10, 2026	65.5
OpenAI: GPT-4.1 Mini openai/gpt-4.1-mini-2025-04-14 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	64.9
OpenAI: GPT-4.1 openai/gpt-4.1-2025-04-14 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	64.6
Qwen: Qwen3 VL 30B A3B Instruct qwen/qwen3-vl-30b-a3b-instruct Sources: openrouter-benchmarks · Last eval Oct 3, 2026	64.6
Qwen: Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	64.3
OpenAI: gpt-oss-20b openai/gpt-oss-20b Sources: openrouter-benchmarks · Last eval Oct 10, 2026	63.8
NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b Sources: openrouter-benchmarks · Last eval Oct 3, 2026	62.9
Z.ai: GLM 4.5 Air z-ai/glm-4.5-air Sources: openrouter-benchmarks · Last eval Aug 1, 2026	62.3
DeepSeek: DeepSeek V3 deepseek/deepseek-chat-v3 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	62.1
Qwen: Qwen3 30B A3B qwen/qwen3-30b-a3b-04-28 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	62.1
Qwen: Qwen3 32B qwen/qwen3-32b-04-28 Sources: openrouter-benchmarks · Last eval Aug 29, 2026	60.8
Qwen: Qwen3 Coder 480B A35B qwen/qwen3-coder-480b-a35b-07-25 Sources: openrouter-benchmarks · Last eval Oct 3, 2026	60.5
Qwen: Qwen3 14B qwen/qwen3-14b-04-28 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	59.2
Google: Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite Sources: openrouter-benchmarks · Last eval Oct 1, 2026	54.9
Z.ai: GLM 4.7 Flash z-ai/glm-4.7-flash-20260119 Sources: openrouter-benchmarks · Last eval Aug 30, 2026	52.8
OpenAI: GPT-4o (2024-08-06) openai/gpt-4o-2024-08-06 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	52
Qwen: Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct Sources: openrouter-benchmarks · Last eval Aug 15, 2026	52
Qwen: Qwen3 VL 8B Instruct qwen/qwen3-vl-8b-instruct Sources: openrouter-benchmarks · Last eval Aug 1, 2026	51.3
DeepSeek: DeepSeek V3 0324 deepseek/deepseek-chat-v3-0324 Sources: openrouter-benchmarks · Last eval Aug 29, 2026	50.8
OpenAI: GPT-4o (2024-05-13) openai/gpt-4o-2024-05-13 Sources: openrouter-benchmarks · Last eval Aug 1, 2026	50.7
OpenAI: GPT-4o openai/gpt-4o Sources: openrouter-benchmarks · Last eval Oct 1, 2026	50.6
inclusionAI: Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin-20260827 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	50.5
OpenAI: GPT-4.1 Nano openai/gpt-4.1-nano-2025-04-14 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	50
Meta: Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct Sources: openrouter-benchmarks · Last eval Oct 10, 2026	47.3
Qwen2.5 72B Instruct qwen/qwen-2.5-72b-instruct Sources: openrouter-benchmarks · Last eval Oct 1, 2026	46
Qwen: Qwen2.5 VL 72B Instruct qwen/qwen2.5-vl-72b-instruct Sources: openrouter-benchmarks · Last eval Sep 1, 2026	44.4
OpenAI: GPT-4o-mini openai/gpt-4o-mini Sources: openrouter-benchmarks · Last eval Oct 1, 2026	43.2
Tencent: Hy-MT2-30B-A3B tencent/hy-mt2-30b-a3b-20260521 Sources: openrouter-benchmarks · Last eval Sep 24, 2026	38.9
Google: Gemma 3 12B google/gemma-3-12b-it Sources: openrouter-benchmarks · Last eval Oct 8, 2026	37.9
Mistral: Mistral Nemo mistralai/mistral-nemo Sources: openrouter-benchmarks · Last eval Jul 18, 2026	33.8
Qwen: Qwen2.5 7B Instruct qwen/qwen-2.5-7b-instruct Sources: openrouter-benchmarks · Last eval Aug 1, 2026	32.8
Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct Sources: openrouter-benchmarks · Last eval Oct 10, 2026	28.5
Sao10K: Llama 3 8B Lunaris sao10k/l3-lunaris-8b Sources: openrouter-benchmarks · Last eval Oct 1, 2026	27.3
Google: Gemma 3 4B google/gemma-3-4b-it Sources: openrouter-benchmarks · Last eval Oct 15, 2026	27.1
Meta: Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct Sources: openrouter-benchmarks · Last eval Aug 1, 2026	11.6
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) google/gemini-3.1-flash-lite-image-20260630 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	10.3
anthropic/claude-opus-5 anthropic/claude-opus-5 Sources: openrouter-benchmarks · Last eval Aug 14, 2026	—
ByteDance Seed: Seed 1.6 bytedance-seed/seed-1.6-20250625 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
ByteDance Seed: Seed-2.0-Lite bytedance-seed/seed-2.0-lite-20260309 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
ByteDance Seed: Seed-2.0-Mini bytedance-seed/seed-2.0-mini-20260224 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
deepseek/deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 Sources: openrouter-benchmarks · Last eval Aug 11, 2026	—
Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview-20260303 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Google: Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-customtools-20260219 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Meta: Muse Spark 1.1 meta/muse-spark-1.1-20260709 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Meta: Muse Spark 1.2 meta/muse-spark-1.2-20260805 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Meta: Muse Spark 1.3 meta/muse-spark-1.3-20260902 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Meta: Muse Wonder meta/muse-wonder-20261012 Sources: openrouter-benchmarks · Last eval Oct 12, 2026	—
OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex-20260224 Sources: openrouter-benchmarks · Last eval Oct 2, 2026	—
openai/gpt-5.6-luna openai/gpt-5.6-luna Sources: openrouter-benchmarks · Last eval Aug 11, 2026	—
openai/gpt-5.6-sol openai/gpt-5.6-sol Sources: openrouter-benchmarks · Last eval Aug 11, 2026	—
Perceptron: Perceptron Mk1 perceptron/perceptron-mk1-20260512 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Perceptron: Perceptron Mk1.5 perceptron/perceptron-mk1.5-20260925 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.5-Flash qwen/qwen3.5-flash-20260224 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.5 Plus 2026-02-15 qwen/qwen3.5-plus-20260216 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.5 Plus 2026-04-20 qwen/qwen3.5-plus-20260420 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.6 Flash qwen/qwen3.6-flash Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.7 Flash qwen/qwen3.7-flash-20260727 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.8 Max (0803) qwen/qwen3.8-max-20260803 Sources: openrouter-benchmarks · Last eval Sep 1, 2026	—
Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-20260902 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash-20260918 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Reka Edge rekaai/reka-edge-2603 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—
Xiaomi: MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed-20260921 Sources: openrouter-benchmarks · Last eval Sep 21, 2026	—
Xiaomi: MiMo-X-Flash Preview xiaomi/mimo-x-flash-preview-20260914 Sources: openrouter-benchmarks · Last eval Sep 14, 2026	—
Xiaomi: MiMo-X-Pro Preview xiaomi/mimo-x-pro-preview-20260914 Sources: openrouter-benchmarks · Last eval Sep 14, 2026	—
Z.ai: GLM 5V Turbo z-ai/glm-5v-turbo-20260401 Sources: openrouter-benchmarks · Last eval Oct 1, 2026	—

193 models · Sources: openrouter-benchmarks · As of Oct 15, 2026

Indexes come from Artificial Analysis; eval pass rates come from OpenRouter in-house evals. Models without an eval show a placeholder in that column, and models with no evals at all stay off the board.

Benchmark numbers are third-party and source-measured results, shown as published with attribution. They are not a recommendation, and figures from different sources are not directly comparable.

No prices here: OpenRouter reference prices use a different basis than the relay quotes on this site. Compare prices on the Token API price page.