Benchmarks

Top models across a combined benchmark plus Artificial Analysis, LMArena, LiveBench, and NanoGPT benchmark categories.

Combined

Equal-weight blend of Artificial Analysis Intelligence Index, LMArena Overall, LiveBench Overall, NanoGPT Usage Share. Each source is min-max normalized to 0-100 across its current leaderboard and weighted at 25%. Missing or unavailable source entries contribute 0.

Top 20 price vs performance

X-axis: $/M blended tokens

1.

Claude 4.7 Opus
Anthropic logo

by Anthropic

82.1%

2.

60.7%

3.

GPT 5.5
OpenAI logo

by OpenAI

54.6%

4.

GPT 5.4
OpenAI logo

by OpenAI

51.9%

5.

Claude 4.6 Opus
Anthropic logo

by Anthropic

50.6%

6.

36.5%

7.

Qwen3.7
Qwen logo

by Qwen

35.1%

8.

GPT 5
OpenAI logo

by OpenAI

34.3%

9.

Claude Sonnet 4.6
Anthropic logo

by Anthropic

21.1%

10.

Claude 4.5 Opus
Anthropic logo

by Anthropic

19.2%

Weighted blend of latest source snapshots

NanoGPT Composite