Model comparison
DeepSeek-V3.1 vs o4-mini
DeepSeek-V3.1 and o4-mini score almost the same on the Noometry Index (42.2 vs 41.6), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
DeepSeekSummary
- They share 26 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 3 categories and o4-mini in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where o4-mini leads 45.5 to 36.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 77.8% for o4-mini.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 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 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | o4-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.2 | 41.6 |
| Released | 2025-08-21 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.25 | $1.10 |
| Output $ / M tokens | $0.95 | $4.40 |
| Results tracked | 27 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
DeepSeek-V3.1: 39.8 (#140), o4-mini: 41.6 (#110)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| WeirdML | 38.4% | 52.6% |
| LMArena Coding | 1417 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, o4-mini: 32.3 (#57)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), o4-mini: 24.6 (#143)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| SimpleBench | 40% | 38.7% |
| Kagi LLM Benchmark | 53.2% | 67.6% |
| LMArena Hard Prompts | 1417 | 1351 |
| DTBench | 82.7% | 77.6% |
| LMCA | 24.3% | 26.5% |
| Epoch Capabilities Index | 139.92 | 145.63 |
| ForecastBench | 58 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
Math o4-mini leads
DeepSeek-V3.1: 36.1 (#125), o4-mini: 40.2 (#79)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| LMArena Math | 1420 | 1390 |
| 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 Too close to call
DeepSeek-V3.1: 43.0 (#86), o4-mini: 43.5 (#83)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 18.6% |
| LMArena Expert | 1403 | 1344 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
DeepSeek-V3.1: —, o4-mini: 39.5 (#46)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), o4-mini: 47.2 (#149)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| LMArena Non-English | 1400 | 1336 |
| LMArena Chinese | 1470 | 1355 |
| LMArena French | 1447 | 1362 |
| LMArena German | 1412 | 1336 |
| LMArena Japanese | 1374 | 1308 |
| LMArena Korean | 1337 | 1313 |
| LMArena Russian | 1405 | 1334 |
| LMArena Spanish | 1429 | 1346 |
Instruction Following o4-mini leads
DeepSeek-V3.1: 74.1 (#105), o4-mini: 75.4 (#63)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1400 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
DeepSeek-V3.1: 36.3 (#227), o4-mini: 45.5 (#31)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| Fiction.LiveBench | 52.8% | 77.8% |
| LMArena Longer Query | 1422 | 1315 |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), o4-mini: 54.2 (#148)
| Benchmark | DeepSeek-V3.1 | o4-mini |
|---|---|---|
| LMArena Text | 1420 | 1353 |
| LMArena Creative Writing | 1401 | 1294 |
| LMArena Multi-Turn | 1408 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1436 | — |
| WildBench | — | 85.4% |
Frequently asked questions
Is DeepSeek-V3.1 better than o4-mini?
DeepSeek-V3.1 and o4-mini score almost the same on the Noometry Index (42.2 vs 41.6), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 or o4-mini?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is DeepSeek-V3.1 or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 41.6 versus 39.8 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 and o4-mini share?
26 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and o4-mini has 60.