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 45.0 to 41.4.
Side by side
| Claude Mythos Preview | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 41.2 | 61.9 |
| 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 | 32 |
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: 67.3 (#6)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | — | 52.1% |
| CursorBench | — | 55.5% |
| LMArena WebDev | — | 1774 |
| FrontierSWE | — | 61.9% |
| SciCode | — | 61% |
| LMArena Coding | — | 1513 |
| ALE-Bench | — | 1,819 |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Mythos Preview: 41.4, Claude Sonnet 5.5: 45.0 (#16)
| 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: 54.0 (#28)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| NYT Connections (extended) | — | 80.5% |
| CritPt | — | 31.4% |
| LMArena Hard Prompts | — | 1495 |
| Mystery Game Puzzles | — | 65% |
| Epoch Capabilities Index | — | 165.03 |
Math Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 87.9 (#6)
| 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% |
| LMArena Math | — | 1510 |
| FrontierMath Erdős | — | 2.9% |
Knowledge Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 66.0 (#12)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | — | 95.6% |
| SimpleQA Verified | — | 46.5% |
| LMArena Expert | — | 1540 |
Multimodal Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 51.5 (#6)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | — | 1289 |
| Furniture Assembly | — | 75% |
Multilingual Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 55.3 (#30)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | — | 1452 |
| LMArena Chinese | — | 1522 |
| LMArena Russian | — | 1451 |
Instruction Following Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 78.3 (#11)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | — | 1495 |
Long Context Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 45.9 (#28)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | — | 1498 |
Writing & Preference Not comparable
Claude Mythos Preview: —, Claude Sonnet 5.5: 66.0 (#40)
| Benchmark | Claude Mythos Preview | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | — | 1471 |
| LMArena Creative Writing | — | 1465 |
| LMArena Multi-Turn | — | 1474 |
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 32.