Model comparison
Claude Sonnet 4.5 vs Deepseek Coder v2
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 7 categories and Deepseek Coder v2 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | Deepseek Coder v2 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 44.1 | 35.9 |
| Released | 2025-09-29 | 2024-06-17 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Deepseek Coder v2: 38.1 (#183)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Coding | 1489 | 1251 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 59.7% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 82.3% |
| MBPP+ | — | 75.1% |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.3 (#32), Deepseek Coder v2: —
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#125), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1462 | 1207 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
| WinoGrande | — | 83.7% |
Math Deepseek Coder v2 leads
Claude Sonnet 4.5: 32.3 (#216), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1449 | 1241 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 94.5% |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1482 | 1181 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
| ARC (AI2) Challenge | — | 64.3% |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Deepseek Coder v2: —
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Deepseek Coder v2: 36.3 (#240)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1425 | 1182 |
| LMArena Chinese | 1459 | 1201 |
| LMArena French | 1458 | 1185 |
| LMArena German | 1427 | 1164 |
| LMArena Japanese | 1390 | 1126 |
| LMArena Korean | 1403 | 1104 |
| LMArena Russian | 1437 | 1188 |
| LMArena Spanish | 1457 | 1153 |
Instruction Following Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 75.0 (#78), Deepseek Coder v2: 61.7 (#242)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1180 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Deepseek Coder v2: 37.0 (#224)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1476 | 1219 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Deepseek Coder v2: 38.2 (#253)
| Benchmark | Claude Sonnet 4.5 | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1439 | 1191 |
| LMArena Creative Writing | 1442 | 1120 |
| LMArena Multi-Turn | 1465 | 1177 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Deepseek Coder v2?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index.
Is Claude Sonnet 4.5 or Deepseek Coder v2 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 38.1 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and Deepseek Coder v2 share?
17 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Deepseek Coder v2 has 24.