Model comparison
Claude Sonnet 5.5 vs DeepSeek-V2.5 (Sep 2024)
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 37.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 8 categories and DeepSeek-V2.5 (Sep 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 35.9.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 61.9 | 37.6 |
| Released | 2026-09-28 | 2024-09-06 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 32 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 67.3 (#6), DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Coding | 1513 | 1309 |
| FrontierCode | 52.1% | — |
| Aider Polyglot | — | 17.8% |
| CursorBench | 55.5% | — |
| LMArena WebDev | 1774 | — |
| FrontierSWE | 61.9% | — |
| SciCode | 61% | — |
| BigCodeBench Instruct | — | 48.6% |
| BigCodeBench Complete | — | 53.2% |
| ALE-Bench | 1,819 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Agentic & Tool Use Not comparable
Claude Sonnet 5.5: 45.0 (#16), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| APEX-Agents | 75.5% | — |
Reasoning Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 54.0 (#28), DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1495 | 1289 |
| NYT Connections (extended) | 80.5% | — |
| CritPt | 31.4% | — |
| Mystery Game Puzzles | 65% | — |
| Epoch Capabilities Index | 165.03 | — |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 87.9 (#6), DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1510 | 1288 |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#12), DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1540 | 1266 |
| GPQA Diamond | 95.6% | — |
| SimpleQA Verified | 46.5% | — |
Multimodal Not comparable
Claude Sonnet 5.5: 51.5 (#6), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Vision | 1289 | — |
| Furniture Assembly | 75% | — |
Multilingual Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 55.3 (#30), DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1452 | 1273 |
| LMArena Chinese | 1522 | 1318 |
| LMArena Russian | 1451 | 1289 |
| LMArena French | — | 1289 |
| LMArena German | — | 1258 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1209 |
| LMArena Spanish | — | 1248 |
Instruction Following Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 78.3 (#11), DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1495 | 1280 |
Long Context Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 45.9 (#28), DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1498 | 1301 |
Writing & Preference Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#40), DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
| Benchmark | Claude Sonnet 5.5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1471 | 1294 |
| LMArena Creative Writing | 1465 | 1285 |
| LMArena Multi-Turn | 1474 | 1297 |
Frequently asked questions
Is Claude Sonnet 5.5 better than DeepSeek-V2.5 (Sep 2024)?
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 37.6 on the Noometry Index.
Is Claude Sonnet 5.5 or DeepSeek-V2.5 (Sep 2024) better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 31.7 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5.5 and DeepSeek-V2.5 (Sep 2024) share?
12 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.