Model comparison
Claude Sonnet 5 vs DeepSeek-V3.1-Terminus
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 8.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. Claude Sonnet 5 scores higher in 7 categories and DeepSeek-V3.1-Terminus in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 35.7.
- The biggest single-benchmark swing is LMCA: 50% for Claude Sonnet 5 and 28.6% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.5 | 42.6 |
| Released | 2026-06-29 | 2025-09-22 |
| Weights | Proprietary | Open |
| Context window | 1M | 164K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $10 | $1 |
| Results tracked | 51 | 16 |
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 (#20), DeepSeek-V3.1-Terminus: 41.5 (#114)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| SciCode | 53.6% | 40.6% |
| LMArena Coding | 1483 | 1426 |
| ALE-Bench | 1,463 | 745.17 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.7 (#16), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 48.2 (#37), DeepSeek-V3.1-Terminus: 25.7 (#126)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| CritPt | 16.9% | 1.7% |
| LMArena Hard Prompts | 1461 | 1427 |
| DTBench | 92.5% | 81.3% |
| LMCA | 50% | 28.6% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 57.4% |
| NYT Connections (extended) | 75.1% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.34 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), DeepSeek-V3.1-Terminus: 35.7 (#138)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1467 | 1402 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
Knowledge Not comparable
Claude Sonnet 5: 55.7 (#42), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| LMArena Expert | 1491 | — |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#26), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Vision | 1275 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 54.0 (#55), DeepSeek-V3.1-Terminus: 52.3 (#87)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1431 | 1407 |
| LMArena Russian | 1452 | 1434 |
| LMArena Chinese | 1475 | — |
| LMArena French | 1457 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.6 (#39), DeepSeek-V3.1-Terminus: 74.4 (#96)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1453 | 1406 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#53), DeepSeek-V3.1-Terminus: 43.5 (#88)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1464 | 1426 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), DeepSeek-V3.1-Terminus: 61.3 (#87)
| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1443 | 1420 |
| LMArena Creative Writing | 1416 | 1404 |
| LMArena Multi-Turn | 1454 | 1411 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than DeepSeek-V3.1-Terminus?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 8.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or DeepSeek-V3.1-Terminus better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 41.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 164K.
How many benchmarks do Claude Sonnet 5 and DeepSeek-V3.1-Terminus share?
15 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.