AI Model Capability Comparison
ML engineering
Only models released within the past year are shown. Only benchmarks covering at least 3 of these models are shown. Unknown release dates are excluded; historical data is retained.
— means no published score for this candidate in this source, not zero.
| No. | Model | 10/11 recent-year models have scores |
|---|---|---|
| 1 |  Claude Opus 5.5 | 31.2xhigh · claude_codeclaude-opus-5-5_xhigh |
| 2 |  GPT-6 Astra | 42.22xhigh · codex_cligpt-6-astra_xhigh |
| 3 | GPT-6.1 Sol | 38.25xhigh · codex_cligpt-6.1-sol_xhigh |
| 4 | Claude Fable 5.1 | 25.97xhigh · claude_codeclaude-fable-5-1_xhigh |
| 5 |  Gemini 4 Argon | 20.22high · gemini_cligemini-4-argon_high |
| 6 | Claude Sonnet 5.5 | 19.94xhigh · claude_codeclaude-sonnet-5-5_xhigh |
| 7 | Claude Opus 5 | 19.01xhigh · claude_codeclaude-opus-5_xhigh |
| 8 | GPT-6 Sol | 19.73xhigh · codex_cligpt-6-sol_xhigh |
| 9 | GPT-6 Luna | 7.87xhigh · codex_cligpt-6-luna_xhigh |
| 10 | Claude Haiku 5.5 | 11.7xhigh · claude_codeclaude-haiku-5-5_xhigh |
| 11 | Claude Mythos Preview | — |
Epoch AI benchmarks
Source: Epoch AI, CC BY 4.0 ↗ · Updated 2026-10-15
WeirdML v3 · Updated 2026-10-12
PandaNpc Updated Oct 21, 2026, 06:01 UTC
Source: Epoch AI, CC BY 4.0 · Vals.ai · Artificial Analysis (artificialanalysis.ai)
Column guide
- No.
- Display order only. Sorting changes this number; it is not a published capability rank.
- Model
- The evaluated model name and its provider icon. A dash in a score column means no published score is available here, not a zero.
- WeirdML v3Unconventional machine learning v3
- Tests machine learning and data analysis on unfamiliar tasks with limited feedback. Its composite progress score is not ordinary classification accuracy. Evaluation methodology ↗
Read scores within the same benchmark, source and version. Higher values indicate stronger performance on the reported metric, but different columns do not share a common scale.