Model comparison
Claude Mythos Preview vs Claude Sonnet 5.5
Claude Sonnet 5.5 has enough public results to be ranked (#10); Claude Mythos Preview does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in agentic & tool use, where Claude Sonnet 5.5 leads 44.9 to 41.1.
Side by side
| Claude Mythos Preview | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 40.8 | 60.5 |
| Released | 2026-04-07 | 2026-09-28 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 2 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 65.5 (#6)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | — | 52.1% |
| CursorBench | — | 55.5% |
| LMArena WebDev | — | 1699 |
| FrontierSWE | — | 61.9% |
| SciCode | — | 61% |
| ALE-Bench | — | 1,819 |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Mythos Preview: 41.1, Claude Sonnet 5.5: 44.9 (#14)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | — | 75.5% |
| ExploitBench | 73.8% | — |
| METR Time Horizons | 85.2% | — |
Reasoning Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 52.4 (#29)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| CritPt | — | 31.4% |
| Mystery Game Puzzles | — | 65% |
Math Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 88.7 (#4)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 88.8% |
| FrontierMath Tier 4 | — | 80.5% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 100% |
Knowledge Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 66.0 (#11)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | — | 95.6% |
| SimpleQA Verified | — | 46.5% |
Multimodal Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 53.2 (#5)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| Furniture Assembly | — | 75% |
Frequently asked questions
Is Claude Mythos Preview better than Claude Sonnet 5.5?
Claude Sonnet 5.5 has enough public results to be ranked (#10); Claude Mythos Preview does not yet, so treat this comparison as directional.
How many benchmarks do Claude Mythos Preview and Claude Sonnet 5.5 share?
0 benchmarks have published results for both models. Claude Mythos Preview has 2 scored results on Noometry and Claude Sonnet 5.5 has 16.