Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief

Compare AI Models

Decision workspace

Pick two of 379 models and compare them side-by-side across 107 benchmarks — updated with every release.

Step 1: Pick Model AStep 2: Pick Model B

Popular Comparisons

Claude Opus 5vsGPT-5.6 Sol

82.8 vs 81.79

GPT-5.6 SolvsClaude Sonnet 5

81.79 vs 64.51

Kimi K3vsGPT-5.6 Sol

80.21 vs 81.79

GPT-5.6 SolvsClaude Opus 4.8

81.79 vs 76.84

GPT-5.6 TerravsGemini 3.5 Flash

72.55 vs 64.26

GPT-5.6 LunavsGemini 3.5 Flash

66.92 vs 64.26

Gemini 3.6 FlashvsGemini 3.5 Flash

75.25 vs 64.26

Gemini 3.5 Flash-LitevsGemini 3.1 Flash-Lite

65.02 vs 50.26

Claude Sonnet 5vsClaude Opus 4.8

64.51 vs 76.84

Claude Opus 4.8vsGPT-5.5

76.84 vs 73.09

Claude Opus 4.8vsClaude Opus 4.7 (Adaptive)

76.84 vs 72.15

Gemini 3.5 FlashvsGPT-5.5

64.26 vs 73.09

Gemini 3.5 FlashvsClaude Opus 4.7

64.26 vs 71.57

Gemini 3.5 FlashvsGemini 3.1 Pro

64.26 vs 55.02

GPT-5.5vsClaude Opus 4.7

73.09 vs 71.57

GPT-5.5vsClaude Opus 4.7 (Adaptive)

73.09 vs 72.15

GPT-5.5vsClaude Fable 5

73.09 vs 82.62

GPT-5.5vsClaude Mythos 5

73.09 vs 82.87

GPT-5.5vsGemini 3.1 Pro

73.09 vs 55.02

GPT-5.5vsGemini 3.1 Flash-Lite

73.09 vs 50.26

GPT-5.5vsGLM-5.2

73.09 vs 62.9

GPT-5.5vsGLM-5.1

73.09 vs 66.63

GPT-5.5vsKimi K2.7 Code

73.09 vs 53.9

GPT-5.5 ProvsClaude Opus 4.7

63.23 vs 71.57

Claude Opus 4.7vsGemini 3.1 Pro

71.57 vs 55.02

GLM-5 (Reasoning)vsGPT-5.5

59.3 vs 73.09

GLM-5.2vsKimi K2.7 Code

62.9 vs 53.9

GLM-5.1vsKimi K2.7 Code

66.63 vs 53.9

Ling 2.6 FlashvsKimi K2.7 Code

43.15 vs 53.9

Ling 2.6 FlashvsGPT-5.5

43.15 vs 73.09

Ling 2.6 FlashvsGLM-5.1

43.15 vs 66.63

Ling 2.6 FlashvsClaude Opus 4.7

43.15 vs 71.57

Qwen3.6-27BvsQwen3.6-35B-A3B

52.78 vs 50.47

Qwen3.6-27BvsQwen3.5-27B

52.78 vs 59.54

Qwen3.6-27BvsGemma 4 31B

52.78 vs 59.86

Claude Mythos 5vsGPT-5.5 Pro

82.87 vs 63.23

Claude Mythos 5vsClaude Opus 4.7

82.87 vs 71.57

Claude Fable 5vsClaude Opus 4.8

82.62 vs 76.84

Claude 3.5 SonnetvsGrok 4

47.18 vs 59.33

GPT-4ovsGrok 4.1

40.57 vs 59.49

Gemini 2.5 Provso3

56.39 vs 46.74

Kimi K2.7 CodevsKimi K2.6

53.9 vs 60

Claude Opus 4.7vsGrok 4.20

71.57 vs 54.24

GPT-4ovsGrok 4

40.57 vs 59.33

Claude 4.1 Opus ThinkingvsGrok 4

35.34 vs 59.33

Claude Opus 4.7vsGrok 4.1 Fast

71.57 vs 50.32

Gemini 3.1 ProvsGrok 3 [Beta]

55.02 vs 39.82

Claude 4 SonnetvsGrok 4

41.72 vs 59.33

Claude Opus 4.7vsGPT-4o

71.57 vs 40.57

AI model comparison FAQ

How do I compare two AI models?

Pick any two models above to see them side-by-side across 107 benchmarks, plus pricing, speed and context window. Popular pairs are linked below the picker.

What is the best AI model comparison tool?

BenchLM compares 379 models across 107 sourced benchmarks, updated with every release — every score links to its original source.

Can I compare ChatGPT, Claude and Gemini?

Yes — any pair, e.g. Claude Opus 5 vs GPT-5.6. For the three-way breakdown see ChatGPT vs Claude vs Gemini.

How often is the comparison data updated?

On every model release and benchmark ingest; see latest model releases.