2 vs 0 benchmarks won
Anthropic Claude Opus 4.6 | OpenAI GPT-5.3-Codex-Spark | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Feb 5 2026 | Feb 12 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | 128k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.3% | — |
Software engineering SWE-Bench Verified | 80.8% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude Opus 4.6 shipped 7 days before GPT-5.3-Codex-Spark | |
Claude Opus 4.6 leads GPT-5.3-Codex-Spark on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Opus 4.6 shipped 7 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.