Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
4 selected
GPT-5.5OpenAIClaude Opus 4.8AnthropicGemini 3.1 Pro PreviewGoogle DeepMindDeepSeek V4 ProDeepSeek
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
| Benchmark | GPT-5.5OpenAI | Claude Opus 4.8Anthropic | Gemini 3.1 Pro PreviewGoogle DeepMind | DeepSeek V4 ProOpenDeepSeek |
|---|---|---|---|---|
| SWE-bench Verified% resolved | 80.6% | 88.6% | 75.6% | 80.6% |
| DeepSWE% resolved | 70.05% | 58% | 9.88% | 7.52% |
| SWE-bench Pro% resolved | 58.6% | 69.2% | 46.10% | 55.4% |
% resolved
88.6%
80.6%
% resolved
58%
7.52%
% resolved
69.2%
55.4%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.