Model comparison
Claude 3.5 Sonnet vs DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 34.6 on the Noometry Index.
Last verified . 27 shared benchmarks.
DeepSeekSummary
- They share 27 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and DeepSeek-V3.2-Exp in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 28.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 87.8% for DeepSeek-V3.2-Exp.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | DeepSeek-V3.2-Exp | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 34.6 | 44.3 |
| Released | 2024-06-20 | 2025-09-29 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.26 |
| Output $ / M tokens | — | $0.38 |
| Results tracked | 60 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 39.0 (#165), DeepSeek-V3.2-Exp: 46.5 (#65)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| Aider Polyglot | 51.6% | 74.2% |
| WeirdML | 40% | 39.5% |
| LMArena Coding | 1342 | 1454 |
| SWE-bench Verified (bash only) | — | 70% |
| LMArena WebDev | — | 1362 |
| SWE-bench Multilingual | — | 59% |
| SciCode | — | 38.9% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Too close to call
Claude 3.5 Sonnet: 32.3 (#67), DeepSeek-V3.2-Exp: 32.7 (#59)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| TheAgentCompany | 24% | 42.9% |
| Terminal-Bench | — | 39.6% |
| APEX-Agents | — | 21.3% |
| Berkeley Function Calling Leaderboard | — | 56.7% |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 1,034 |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), DeepSeek-V3.2-Exp: 22.1 (#208)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1434 |
| DTBench | 67.8% | 87.7% |
| Epoch Capabilities Index | 133.55 | 146.27 |
| ARC-AGI-2 | — | 4% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 36.7% |
| ARC-AGI-1 | — | 57% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 14% |
| EnigmaEval | 0.9% | — |
| Thematic Generalization | — | 65% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 29.1% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 19.2 (#288), DeepSeek-V3.2-Exp: 41.7 (#87)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 87.8% |
| LMArena Math | 1307 | 1435 |
| FrontierMath (Feb 2025 set) | 2.1% | 22.1% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| MathArena Final-Answer Competitions | — | 57.7% |
| ProofBench | — | 8% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
Knowledge DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 28.6 (#245), DeepSeek-V3.2-Exp: 51.7 (#66)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| GPQA Diamond | 55.3% | 83.4% |
| LMArena Expert | 1265 | 1436 |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 5.3% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), DeepSeek-V3.2-Exp: —
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 43.2 (#185), DeepSeek-V3.2-Exp: 52.2 (#90)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Non-English | 1283 | 1409 |
| LMArena Chinese | 1272 | 1461 |
| LMArena French | 1305 | 1433 |
| LMArena German | 1297 | 1440 |
| LMArena Japanese | 1234 | 1374 |
| LMArena Korean | 1200 | 1371 |
| LMArena Russian | 1306 | 1424 |
| LMArena Spanish | 1290 | 1440 |
Instruction Following DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 68.8 (#182), DeepSeek-V3.2-Exp: 74.5 (#93)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Instruction Following | 1297 | 1413 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 39.9 (#167), DeepSeek-V3.2-Exp: 47.6 (#16)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Longer Query | 1311 | 1428 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | — | 13.2% |
| CL-bench Life | — | 9.5% |
Writing & Preference DeepSeek-V3.2-Exp leads
Claude 3.5 Sonnet: 52.9 (#164), DeepSeek-V3.2-Exp: 62.4 (#77)
| Benchmark | Claude 3.5 Sonnet | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Text | 1298 | 1425 |
| LMArena Creative Writing | 1292 | 1403 |
| EQ-Bench Creative Writing | 1451 | 1515 |
| LMArena Multi-Turn | 1326 | 1427 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than DeepSeek-V3.2-Exp?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or DeepSeek-V3.2-Exp better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and DeepSeek-V3.2-Exp share?
27 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and DeepSeek-V3.2-Exp has 49.