Model comparison
DeepSeek-V3.1-Terminus vs o4-mini
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 4 categories and o4-mini in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 54.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 67.6% for o4-mini.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- o4-mini accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | o4-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 41.6 |
| Released | 2025-09-22 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 147K | 100K |
| Input $ / M tokens | $0.27 | $1.10 |
| Output $ / M tokens | $1 | $4.40 |
| Results tracked | 16 | 60 |
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: 42.0 (#113), o4-mini: 40.9 (#127)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Coding | 1426 | 1368 |
| ALE-Bench | 745.17 | 826.17 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| SciCode | 40.6% | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, o4-mini: 32.6 (#61)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), o4-mini: 24.6 (#162)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 67.6% |
| CritPt | 1.7% | 0.6% |
| LMArena Hard Prompts | 1426 | 1351 |
| DTBench | 81.3% | 77.6% |
| LMCA | 28.6% | 26.5% |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| ARC-AGI-1 | — | 58.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
DeepSeek-V3.1-Terminus: 38.5 (#137), o4-mini: 40.8 (#89)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Math | 1402 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, o4-mini: 43.6 (#91)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
| LMArena Expert | — | 1343 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, o4-mini: 40.2 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), o4-mini: 47.0 (#154)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Non-English | 1407 | 1337 |
| LMArena Russian | 1436 | 1334 |
| LMArena Chinese | — | 1354 |
| LMArena French | — | 1364 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1312 |
| LMArena Spanish | — | 1347 |
Instruction Following o4-mini leads
DeepSeek-V3.1-Terminus: 74.0 (#106), o4-mini: 75.2 (#68)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1404 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
DeepSeek-V3.1-Terminus: 43.4 (#97), o4-mini: 45.5 (#33)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Longer Query | 1421 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), o4-mini: 54.0 (#152)
| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Text | 1419 | 1353 |
| LMArena Creative Writing | 1403 | 1294 |
| LMArena Multi-Turn | 1411 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than o4-mini?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.6 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or o4-mini?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is DeepSeek-V3.1-Terminus or o4-mini better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and o4-mini share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and o4-mini has 60.