Model comparison
Claude Opus 4.1 vs DeepSeek-V2.5 (Sep 2024)
Claude Opus 4.1 is the stronger model overall, scoring 40.8 to 37.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Claude Opus 4.1 scores higher in 7 categories and DeepSeek-V2.5 (Sep 2024) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4.1 leads 44.3 to 31.3.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 40.8 | 37.0 |
| Released | 2025-08-05 | 2024-09-06 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 32K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $75 | — |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.3 (#69), DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Coding | 1479 | 1310 |
| SWE-bench Verified | 73.3% | — |
| Aider Polyglot | — | 17.8% |
| LMArena WebDev | 1390 | — |
| WeirdML | 45.9% | — |
| BigCodeBench Instruct | — | 48.6% |
| BigCodeBench Complete | — | 53.2% |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Agentic & Tool Use Not comparable
Claude Opus 4.1: 34.8 (#38), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 31.6 (#70), DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1289 |
| SimpleBench | 60% | — |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LMCA | 37.1% | — |
| Epoch Capabilities Index | 144.11 | — |
| ForecastBench | 62 | — |
Math DeepSeek-V2.5 (Sep 2024) leads
Claude Opus 4.1: 22.0 (#267), DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1430 | 1289 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 41.9 (#93), DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1439 | 1266 |
| GPQA Diamond | 77.3% | — |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Not comparable
Claude Opus 4.1: 26.2 (#114), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| VPCT | 35% | — |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.1 (#90), DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1405 | 1273 |
| LMArena Chinese | 1427 | 1317 |
| LMArena French | 1432 | 1288 |
| LMArena German | 1412 | 1258 |
| LMArena Japanese | 1378 | 1228 |
| LMArena Korean | 1381 | 1209 |
| LMArena Russian | 1421 | 1289 |
| LMArena Spanish | 1448 | 1248 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.8 (#53), DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1436 | 1280 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#60), DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1455 | 1301 |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.6 (#70), DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
| Benchmark | Claude Opus 4.1 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1419 | 1294 |
| LMArena Creative Writing | 1412 | 1285 |
| LMArena Multi-Turn | 1444 | 1297 |
| Short-Story Creative Writing | 84.7% | — |
Frequently asked questions
Is Claude Opus 4.1 better than DeepSeek-V2.5 (Sep 2024)?
Claude Opus 4.1 is the stronger model overall, scoring 40.8 to 37.0 on the Noometry Index.
Is Claude Opus 4.1 or DeepSeek-V2.5 (Sep 2024) better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 31.3 in the Noometry coding category.
How many benchmarks do Claude Opus 4.1 and DeepSeek-V2.5 (Sep 2024) share?
17 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.