Claude 3.7 Sonnet
Anthropic
Highlights
Top benchmark results for anthropic/claude-3-7-sonnet-2025-02-24.
975#15
2233#6
0.65#9
0.80#18
0.29#16
0.01#16
19.76#29
6.31#3
1083#20
0.85#8
166#8
0.67#9
1385#17
1357#5
0.34#17
0.46#7
1.88#9
Benchmark table
Detailed scores across tracked benchmarks.
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| Ai2 SciArena | - | 975 | - | No | Source |
| AidanBench | - | 2233 | Thinking | No | Source |
| Aider-Polyglot | code | 0.65 | 32k Thinking | No | Source |
| AIME 2024 | math | 0.80 | 64k Thinking | Yes | Source |
| ARC-AGI-1 | - | 0.29 | 16k Thinking | No | Source |
| ARC-AGI-2 | - | 0.01 | 8k Thinking | No | Source |
| Confabulations | - | 19.76 | - | No | Source |
| Elimation Game | - | 6.31 | 16k Thinking | No | Source |
| EQ-Bench 3 | - | 1083 | - | No | Source |
| GPQA Diamond | general-knowledge | 0.85 | - | Yes | Source |
| LisanBench | - | 166 | - | No | Source |
| LiveBench | - | 0.67 | 64k Thinking | No | Source |
| LMArena Text | - | 1385 | 32k Thinking | No | Source |
| LMArena WebDev | - | 1357 | 16th June 2025 | No | Source |
| NYT Connections | - | 0.34 | 16k Thinking | No | Source |
| SimpleBench | - | 0.46 | Thinking | No | Source |
| Thematic Generalisation | - | 1.88 | - | No | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
LMArena WebDev
Compare this model with the leading peers for the selected benchmark.
Benchmark
1357
Rank #5/21
21 models
Showing 11 models around the selected model (out of 21 total).