← the bench index

AI model comparisons

Head-to-head results from the public leaderboards ArtificialWatch reads every day. Each page shows every board that scores both models, with the board's own number. Nothing here is our opinion. For price alone, every live model's API price is in one table. Table composed November 8, 2026.

116 comparisons across 34 models. Each model's section lists every comparison it is in, and each line counts the boards that rate both and on how many that model scores higher or lower.

Claude Opus 5

16 comparisons · Claude Opus 5 tracker

GPT-6 Astra

15 comparisons · GPT-6 Astra tracker

Claude Fable 5

14 comparisons · Claude Fable 5 tracker

Claude Opus 4.8

12 comparisons · Claude Opus 4.8 tracker

Claude Opus 5.5

11 comparisons · Claude Opus 5.5 tracker

GPT-5.6

11 comparisons · GPT-5.6 tracker

Claude Fable 5.1

10 comparisons · Claude Fable 5.1 tracker

Gemini 3.8 Flash

10 comparisons · Gemini 3.8 Flash tracker

Kimi K3

10 comparisons · Kimi K3 tracker

Claude Sonnet 5

9 comparisons · Claude Sonnet 5 tracker

Claude Sonnet 5.5

9 comparisons · Claude Sonnet 5.5 tracker

DeepSeek V4 Pro

9 comparisons · DeepSeek V4 Pro tracker

GLM-5.3

9 comparisons · GLM-5.3 tracker

GLM-5.2

8 comparisons · GLM-5.2 tracker

Grok 4.6

8 comparisons · Grok 4.6 tracker

Qwen 3.8 Max

8 comparisons · Qwen 3.8 Max tracker

GPT-5.5

7 comparisons · GPT-5.5 tracker

GPT-6.1 Sol

7 comparisons · GPT-6.1 Sol tracker

Muse Spark 1.3

7 comparisons · Muse Spark 1.3 tracker

GPT-6.1 Terra

6 comparisons · GPT-6.1 Terra tracker

Claude Haiku 5.5

5 comparisons · Claude Haiku 5.5 tracker

GPT-6 Luna

5 comparisons · GPT-6 Luna tracker

GPT-6 Sol

4 comparisons · GPT-6 Sol tracker

MiniMax M3

4 comparisons · MiniMax M3 tracker

Gemini 4 Argon

3 comparisons · Gemini 4 Argon tracker

Grok 4.7

3 comparisons · Grok 4.7 tracker

DeepSeek V4.1 Flash

2 comparisons · DeepSeek V4.1 Flash tracker

Gemini 3.1 Pro

2 comparisons · Gemini 3.1 Pro tracker

Gemini 3.5 Flash

2 comparisons · Gemini 3.5 Flash tracker

GLM-5.3 Flash

2 comparisons · GLM-5.3 Flash tracker

Grok 4.5

1 comparison · Grok 4.5 tracker

Kimi K3.1 Pro

1 comparison · Kimi K3.1 Pro tracker

Mistral Large 4

1 comparison · Mistral Large 4 tracker

Muse Wonder

1 comparison · Muse Wonder tracker