Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Compare any two AI models

Head to head on the tests both models actually ran, with every number linked to its source.

949 matchups ready to read, across 110 models

Every Matchup

949 comparisons across 110 models. Choose a maker, then a model, to see every model it has been measured against.

Alibaba models
Qwen3.5 397B A17B39 matchups

Most tests in common first.About Qwen3.5 397B A17B

Show all 39 matchups
Qwen3.5 35B A3B35 matchups
Qwen3.5 27B33 matchups
Qwen3.5 122B A10B28 matchups
Qwen3.6 35B A3B27 matchups
Qwen3.7 Max11 matchups
Qwen3.5 2B9 matchups
Qwen2.5 Instruct 72B8 matchups
Qwen3.5 4B8 matchups
Qwen3.6 27B8 matchups
Qwen3.7 Plus Preview6 matchups
Qwen3.6 Plus5 matchups
Qwen3.8 Flash Next5 matchups
Qwen3.8 27B4 matchups
Qwen3 VL 4B (Reasoning)3 matchups
Qwen3 VL 4B Instruct3 matchups
Qwen3.8 Max Preview3 matchups
Qwen3.8 2.4T A95B2 matchups
Qwen3.5 0.8B1 matchup
Qwen3.5 9B1 matchup
All 20 Alibaba models
OpenAI models
GPT-5.551 matchups

Most tests in common first.About GPT-5.5

Show all 51 matchups
GPT-5.6 Sol50 matchups

Most tests in common first.About GPT-5.6 Sol

Show all 50 matchups
GPT-5.247 matchups

Most tests in common first.About GPT-5.2

Show all 47 matchups
GPT-5.443 matchups
GPT-537 matchups
GPT-5.6 Luna35 matchups
GPT-5.133 matchups
GPT-6 Astra30 matchups
GPT-6.1 Sol21 matchups
GPT-4o20 matchups
o319 matchups
o4-mini17 matchups
GPT-4o mini13 matchups
o19 matchups
GPT-5.6 Terra5 matchups
GPT-6 Sol5 matchups
GPT-5.3-Codex1 matchup
GPT-5.5 Pro1 matchup
o3-mini1 matchup

Most tests in common first.About o3-mini

All 19 OpenAI models
Anthropic models
Claude Opus 4.850 matchups

Most tests in common first.About Claude Opus 4.8

Show all 50 matchups
Claude Opus 4.746 matchups

Most tests in common first.About Claude Opus 4.7

Show all 46 matchups
Claude Opus 4.644 matchups

Most tests in common first.About Claude Opus 4.6

Show all 44 matchups
Claude Opus 4.543 matchups

Most tests in common first.About Claude Opus 4.5

Show all 43 matchups
Claude Sonnet 4.543 matchups

Most tests in common first.About Claude Sonnet 4.5

Show all 43 matchups
Claude Sonnet 4.642 matchups

Most tests in common first.About Claude Sonnet 4.6

Show all 42 matchups
Claude Fable 539 matchups

Most tests in common first.About Claude Fable 5

Show all 39 matchups
Claude Opus 534 matchups
Claude Fable 5.132 matchups
Claude Sonnet 431 matchups
Claude Opus 5.529 matchups
Claude Sonnet 527 matchups
Claude 3.5 Sonnet16 matchups
Claude Sonnet 5.513 matchups
Claude Opus 411 matchups
Claude 3.7 Sonnet10 matchups
Claude 3 Opus1 matchup
All 17 Anthropic models
Google models
Gemini 3.1 Pro52 matchups

Most tests in common first.About Gemini 3.1 Pro

Show all 52 matchups
Gemini 3 Pro39 matchups
Gemini 3.5 Flash37 matchups

Most tests in common first.About Gemini 3.5 Flash

Show all 37 matchups
Gemma 4 26B A4B34 matchups
Gemini 2.5 Pro33 matchups
Gemini 4 Argon8 matchups
Gemma 4 E2B8 matchups
Gemini 3.8 Flash7 matchups
Gemini 2.5 Flash6 matchups
Gemini 3.7 Flash5 matchups
Gemma 4 E4B5 matchups
Gemini 1.5 Pro3 matchups
Gemini 3.6 Flash3 matchups
Gemma 4 31B2 matchups
All 14 Google models
DeepSeek models
DeepSeek-V4-Pro44 matchups

Most tests in common first.About DeepSeek-V4-Pro

Show all 44 matchups
DeepSeek-V4-Flash43 matchups

Most tests in common first.About DeepSeek-V4-Flash

Show all 43 matchups
DeepSeek-V3.234 matchups
DeepSeek-V4.1-Flash26 matchups
DeepSeek-V316 matchups
DeepSeek-R13 matchups
DeepSeek-V4-Flash-Vision-Exp1 matchup
Meta models
Muse Spark 1.121 matchups
Llama 3.1 Instruct 405B9 matchups
Muse Spark 1.24 matchups
Muse Spark2 matchups
Muse Spark 1.31 matchup
NVIDIA models
Nemotron 3 Ultra 550B A55B28 matchups
Nemotron 3 Super 120B A12B8 matchups
Llama 3.1 Nemotron Ultra 253B V11 matchup
Nemotron 3 Ultra 550B A55B Base1 matchup
Nemotron 3.5 Lightning1 matchup
Z.ai models
GLM-5.236 matchups
GLM-5.132 matchups
GLM-5.34 matchups
GLM-4.61 matchup
GLM-5.3-Flash1 matchup
Moonshot models
Kimi K2.640 matchups
Kimi K2.537 matchups
Kimi K335 matchups
Kimi K2 Thinking1 matchup
IBM models
Granite 4.2 30B1 matchup
Granite 4.2 3B1 matchup
Granite 4.2 8B1 matchup
ByteDance models
SpaceXAI models
Xiaomi models
Liquid AI models
LFM2.5-8B-A1B1 matchup
Motif Technologies models
Motif-3-Beta1 matchup
Sapiens AI models
Agnes 2.5 Pro Beta1 matchup
StepFun models
Thinking Machines models