Model comparison
DeepSeek-V3.1-Terminus vs o1-mini
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 33.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and o1-mini in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 8.9.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | o1-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 33.7 |
| Released | 2025-09-22 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), o1-mini: 35.1 (#218)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Coding | 1426 | 1362 |
| Aider Polyglot | — | 32.9% |
| SciCode | 40.6% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, o1-mini: 24.3 (#112)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), o1-mini: 8.9 (#340)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1333 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 57.4% | — |
| ARC-AGI-1 | — | 14% |
| CritPt | 1.7% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 81.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 135.82 |
| LiveBench | — | 57.8% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), o1-mini: 33.7 (#168)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Math | 1402 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, o1-mini: 34.8 (#180)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), o1-mini: 43.8 (#177)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Non-English | 1407 | 1289 |
| LMArena Russian | 1434 | 1283 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1292 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Spanish | — | 1302 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), o1-mini: 67.0 (#200)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1406 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), o1-mini: 40.1 (#156)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Longer Query | 1426 | 1321 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), o1-mini: 48.6 (#196)
| Benchmark | DeepSeek-V3.1-Terminus | o1-mini |
|---|---|---|
| LMArena Text | 1420 | 1317 |
| LMArena Creative Writing | 1404 | 1244 |
| LMArena Multi-Turn | 1411 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than o1-mini?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 33.7 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or o1-mini better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 35.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and o1-mini share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and o1-mini has 39.