Model comparison
Claude Opus 4.1 vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. Claude Opus 4.1 scores higher in 5 categories and DeepSeek-V3.1-Terminus in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 22.3.
- The biggest single-benchmark swing is LMCA: 37.1% for Claude Opus 4.1 and 28.6% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Opus 4.1 accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 41.0 | 43.1 |
| Released | 2025-08-05 | 2025-09-22 |
| Weights | Proprietary | Open |
| Context window | 200K | 164K |
| Max output | 32K | 147K |
| Input $ / M tokens | $15 | $0.27 |
| Output $ / M tokens | $75 | $1 |
| Results tracked | 48 | 16 |
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: 44.4 (#73), DeepSeek-V3.1-Terminus: 42.0 (#113)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1479 | 1426 |
| ALE-Bench | 674.77 | 745.17 |
| SWE-bench Verified | 73.3% | — |
| LMArena WebDev | 1390 | — |
| SciCode | — | 40.6% |
| WeirdML | 45.9% | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.1: 35.0 (#41), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| 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: 32.2 (#76), DeepSeek-V3.1-Terminus: 26.4 (#133)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1426 |
| DTBench | 80% | 81.3% |
| LMCA | 37.1% | 28.6% |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| Epoch Capabilities Index | 144.12 | — |
| ForecastBench | 62 | — |
Math DeepSeek-V3.1-Terminus leads
Claude Opus 4.1: 22.3 (#277), DeepSeek-V3.1-Terminus: 38.5 (#137)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1431 | 1402 |
| 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 Not comparable
Claude Opus 4.1: 42.0 (#101), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 77.3% | — |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
| LMArena Expert | 1439 | — |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), DeepSeek-V3.1-Terminus: —
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| VPCT | 35% | — |
Multilingual Too close to call
Claude Opus 4.1: 52.0 (#95), DeepSeek-V3.1-Terminus: 52.1 (#92)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1405 | 1407 |
| LMArena Russian | 1422 | 1436 |
| LMArena Chinese | 1427 | — |
| LMArena French | 1431 | — |
| LMArena German | 1413 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), DeepSeek-V3.1-Terminus: 74.0 (#106)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1435 | 1404 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), DeepSeek-V3.1-Terminus: 43.4 (#97)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1455 | 1421 |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), DeepSeek-V3.1-Terminus: 61.0 (#92)
| Benchmark | Claude Opus 4.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1419 | 1419 |
| LMArena Creative Writing | 1412 | 1403 |
| LMArena Multi-Turn | 1444 | 1411 |
| Short-Story Creative Writing | 84.7% | — |
Frequently asked questions
Is Claude Opus 4.1 better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or DeepSeek-V3.1-Terminus better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.1 does, with 200K tokens against 164K.
How many benchmarks do Claude Opus 4.1 and DeepSeek-V3.1-Terminus share?
13 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.