Model comparison
Claude Sonnet 5 vs DeepSeek-V2.5 (Sep 2024)
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Claude Sonnet 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 leads 66.2 to 35.9.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.6 | 37.6 |
| Released | 2026-06-29 | 2024-09-06 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Coding | 1483 | 1309 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 17.8% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| BigCodeBench Instruct | — | 48.6% |
| BigCodeBench Complete | — | 53.2% |
| ALE-Bench | 1,463 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1289 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.21 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1467 | 1288 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1490 | 1266 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1431 | 1273 |
| LMArena Chinese | 1477 | 1318 |
| LMArena French | 1460 | 1289 |
| LMArena German | 1440 | 1258 |
| LMArena Japanese | 1422 | 1228 |
| LMArena Korean | 1411 | 1209 |
| LMArena Russian | 1451 | 1289 |
| LMArena Spanish | 1437 | 1248 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1452 | 1280 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1463 | 1301 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
| Benchmark | Claude Sonnet 5 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1442 | 1294 |
| LMArena Creative Writing | 1416 | 1285 |
| LMArena Multi-Turn | 1454 | 1297 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than DeepSeek-V2.5 (Sep 2024)?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.6 on the Noometry Index.
Is Claude Sonnet 5 or DeepSeek-V2.5 (Sep 2024) better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 31.7 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and DeepSeek-V2.5 (Sep 2024) share?
17 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.