SWE Bench Pro
AI benchmark results and model performance
Type: percentage
Recorded results
40
Average score
58.65%
Score range
46% - 80.30%
Leading model
80.30% - Claude Fable 5
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Claude Fable 5 | 09 Jun 2026 | 80.30% | Higher of Mythos 5 / Fable 5 in Anthropic's launch table | Yes | Source | |
| Claude Mythos 5 | 09 Jun 2026 | 80.30% | Higher of Mythos 5 / Fable 5 in Anthropic's launch table | Yes | Source | |
| Claude Opus 5 | 24 Jul 2026 | 79.20% | Adaptive thinking at max effort; default sampling settings; average of 5 trials | Yes | Source | |
| Claude Mythos Preview | 07 Apr 2026 | 77.80% | - | Yes | Source | |
| Fugu Ultra | 22 Jun 2026 | 73.70% | Sakana Fugu product page benchmark table. | Yes | Source | |
| Claude Opus 4.8 | 28 May 2026 | 69.20% | Max effort; avg 5 trials | Yes | Source | |
| Claude Opus 4.7 | 16 Apr 2026 | 64.30% | - | Yes | Source | |
| Claude Sonnet 5 | 30 Jun 2026 | 63.20% | SWE-bench Pro; standard configuration; average over five trials | Yes | Source | |
| Qwen 3.8 27B | 14 Aug 2026 | 61.70% | - | Yes | Source | |
| Muse Spark 1.1 | 09 Jul 2026 | 61.50% | Diverse software engineering | Yes | Source | |
| Qwen 3.7 Max | 21 May 2026 | 60.60% | SWE-Pro; refined benchmark; internal agent scaffold | Yes | Source | |
| Laguna S 2.1 | 21 Jul 2026 | 59.40% | public dataset mean pass@1 | Yes | Source | |
| MiniMax M3 | 01 Jun 2026 | 59% | - | Yes | Source | |
| Fugu | 22 Jun 2026 | 59% | Sakana Fugu product page benchmark table. | Yes | Source | |
| GPT 5.5 | 23 Apr 2026 | 58.60% | Public | Yes | Source | |
| GLM 5.1 | 07 Apr 2026 | 58.40% | - | Yes | Source | |
| GPT 5 Pro | 07 Aug 2025 | 57.70% | inferred family alias from gpt-5.4 (score=0.4083; benches=19) | Yes | Source | |
| GPT 5 Search API | 14 Oct 2025 | 57.70% | inferred family alias from gpt-5.4 (score=0.3050; benches=19) | Yes | Source | |
| GPT 5.4 | 05 Mar 2026 | 57.70% | Public | Yes | Source | |
| GPT 5.3 Codex | 05 Feb 2026 | 56.80% | Public; xhigh reasoning | Yes | Source | |
| Qwen 3.6 Plus | 01 Apr 2026 | 56.60% | - | Yes | Source | |
| GPT 5.2 Codex | 18 Dec 2025 | 56.40% | - | Yes | Source | |
| MiniMax M2.7 | 18 Mar 2026 | 56.20% | - | Yes | Source | |
| MiMo V2.5 | 23 Apr 2026 | 56.10% | Hugging Face evaluation result | Yes | Source | |
| GPT 5.2 | 11 Dec 2025 | 55.60% | - | Yes | Source |
