Claude Sonnet 5 vs Claude Sonnet 5.5
| Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|
| Released | ||
| Lineup | Fable › Opus › Sonnet › Haiku | Fable › Opus › Sonnet › Haiku |
| Input / 1M tokens | $2 | $2 |
| Cached input / 1M tokens | $0.20 | $0.10 |
| Output / 1M tokens | $10 | $10 |
| Context window | 1M | 1M |
| Output limit | 128K | 128K |
| Benchmarks | ||
| Humanity's Last Exam No tools, full set (2,500 questions) | 43.2% | 56.9% |
| Humanity's Last Exam With tools, full set (2,500 questions) | 57.4% | 64.5% |
| SWE-bench Pro Set not specified | 63.2% | 81.3%1 |
| SWE-bench Pro V2 Full set (642 tasks) | 93.15%2Claude Code | 95.79%3mini-SWE-agent |
| SWE-bench Pro V2 HARD-51 (51 tasks) | 88.20%4Claude Code | 70.59%5mini-SWE-agent |
| Terminal-Bench 4.1 | 12.1%6 | 63.9%7 |
| AutomationBench 1.0.6 Private set | 10.7%8 | 44.7%9 |
| OSWorld 2.1 Full set (108 tasks), partial score | 57.0%10 | 80.1%11 |
| OSWorld 2.1 Full set (108 tasks), strict pass rate | 25.6%12 | 43.5%13 |
| Chartography No tools | 16.0%14 | 61.6% |
| Chartography With tools | 71.8%15 | 90.2%16 |
| ExploitGym Mitigations off, successful exploits | 51 of 86917 | 231 of 86918 |
| Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|
| Other benchmarks | ||
| BrowseComp | 84.7%19 | No data |
| Terminal-Bench 4.0 | No data | 70.6%20 |
| Terminal-Bench Science 0.1 | No data | 59.9%21 |
| AutomationBench, release not specified Private set | 13.5%22 | No data |
| OSWorld 2.1 Offline set (82 tasks), partial score | No data | 83.9%23 |
| OSWorld 2.1 Offline set (82 tasks), strict pass rate | No data | 48.8%24 |
| FrontierCode 1.1 Main set | No data | 52.1%25 |
| FrontierCode 1.1 Extended set | No data | 64.4%26 |
| FrontierCode 2.0 Score, all tasks (132) | No data | 42.2%27 |
| FrontierCode 2.0 Pass rate, all tasks (132) | No data | 46.4%28 |
| FrontierSWE v2 | No data | 61.9%29 |
| DeepSWE v1.1 | No data | 71.0%30 |
| Terminal-Bench 2.1 | 80.4% | No data |
| OSWorld-Verified | 81.2%31 | No data |
Notes
- SWE-bench Pro, Set not specified, Claude Sonnet 5.5: max effort · adaptive thinking · average of 5 trials
- SWE-bench Pro V2, Full set (642 tasks), Claude Sonnet 5: Scale AI’s leaderboard, 18 Nov 2026 · Claude Code · xhigh effort
- SWE-bench Pro V2, Full set (642 tasks), Claude Sonnet 5.5: Scale AI’s leaderboard, 18 Nov 2026 · mini-swe-agent · xhigh effort
- SWE-bench Pro V2, HARD-51 (51 tasks), Claude Sonnet 5: Scale AI’s leaderboard, 18 Nov 2026 · Claude Code · xhigh effort
- SWE-bench Pro V2, HARD-51 (51 tasks), Claude Sonnet 5.5: Scale AI’s leaderboard, 18 Nov 2026 · mini-swe-agent · xhigh effort
- Terminal-Bench 4.1, Claude Sonnet 5: Stanford University and Laude Institute’s leaderboard, 18 Nov 2026 · Claude Code · max effort
- Terminal-Bench 4.1, Claude Sonnet 5.5: Stanford University and Laude Institute’s leaderboard, 18 Nov 2026 · Claude Code · max effort
- AutomationBench 1.0.6, Private set, Claude Sonnet 5: Run by Zapier
- AutomationBench 1.0.6, Private set, Claude Sonnet 5.5: Run by Zapier · max effort · default fallbacks on
- OSWorld 2.1, Full set (108 tasks), partial score, Claude Sonnet 5: max effort · mean of 5 runs · September 10, 2026 task files
- OSWorld 2.1, Full set (108 tasks), partial score, Claude Sonnet 5.5: max effort · mean of 5 runs · September 10, 2026 task files
- OSWorld 2.1, Full set (108 tasks), strict pass rate, Claude Sonnet 5: max effort · mean of 5 runs · September 10, 2026 task files
- OSWorld 2.1, Full set (108 tasks), strict pass rate, Claude Sonnet 5.5: max effort · mean of 5 runs · September 10, 2026 task files
- Chartography, No tools, Claude Sonnet 5: max effort · adaptive thinking · average of 5 runs
- Chartography, With tools, Claude Sonnet 5: max effort · adaptive thinking · average of 5 runs · container and image-cropping tool
- Chartography, With tools, Claude Sonnet 5.5: max effort · adaptive thinking · average of 5 runs · container and image-cropping tool · Gemini 3.5 Flash grader
- ExploitGym, Mitigations off, successful exploits, Claude Sonnet 5: 6h wall-clock budget · agent judge confirms the intended vulnerability
- ExploitGym, Mitigations off, successful exploits, Claude Sonnet 5.5: 6h wall-clock budget · agent judge confirms the intended vulnerability
- BrowseComp, Claude Sonnet 5: max effort · adaptive thinking · 10M-token limit, compaction at 200K tokens
- Terminal-Bench 4.0, Claude Sonnet 5.5: adaptive thinking
- Terminal-Bench Science 0.1, Claude Sonnet 5.5: Claude Code in --bare mode · max effort · standard error ±4.7 points
- AutomationBench, release not specified, Private set, Claude Sonnet 5: Run by Zapier · max effort
- OSWorld 2.1, Offline set (82 tasks), partial score, Claude Sonnet 5.5: max effort · mean of 5 attempts
- OSWorld 2.1, Offline set (82 tasks), strict pass rate, Claude Sonnet 5.5: max effort · mean of 5 attempts
- FrontierCode 1.1, Main set, Claude Sonnet 5.5: Run by Cognition · Claude Code harness · xhigh effort
- FrontierCode 1.1, Extended set, Claude Sonnet 5.5: Run by Cognition · Claude Code harness · xhigh effort
- FrontierCode 2.0, Score, all tasks (132), Claude Sonnet 5.5: Cognition’s leaderboard, 18 Nov 2026 · Claude Code · max effort
- FrontierCode 2.0, Pass rate, all tasks (132), Claude Sonnet 5.5: Cognition’s leaderboard, 18 Nov 2026 · Claude Code · max effort
- FrontierSWE v2, Claude Sonnet 5.5: Run by Proximal · Proximal's agent harness · max reasoning effort · mean of 5 trials per task · 20-hour budget
- DeepSWE v1.1, Claude Sonnet 5.5: average of 5 trials
- OSWorld-Verified, Claude Sonnet 5: revised run method with zoom tool fix and 128K max tokens per turn