Model comparison
DeepSeek-V2.5 (Sep 2024) vs o3-mini
DeepSeek-V2.5 (Sep 2024) and o3-mini score almost the same on the Noometry Index (37.0 vs 36.7), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 3 categories and o3-mini in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3-mini leads 41.4 to 31.3.
- The biggest single-benchmark swing is Aider Polyglot: 17.8% for DeepSeek-V2.5 (Sep 2024) and 60.4% for o3-mini.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | o3-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.0 | 36.7 |
| Released | 2024-09-06 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 22 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), o3-mini: 41.4 (#116)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| Aider Polyglot | 17.8% | 60.4% |
| LMArena Coding | 1310 | 1378 |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 48.6% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 53.2% | — |
| CadEval | — | 54% |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, o3-mini: 29.3 (#79)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), o3-mini: 16.3 (#295)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1366 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.35 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), o3-mini: 27.6 (#236)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Math | 1289 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), o3-mini: 38.3 (#135)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Expert | 1266 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
Multilingual o3-mini leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), o3-mini: 45.9 (#159)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Non-English | 1273 | 1319 |
| LMArena Chinese | 1317 | 1379 |
| LMArena French | 1288 | 1333 |
| LMArena German | 1258 | 1303 |
| LMArena Japanese | 1228 | 1286 |
| LMArena Korean | 1209 | 1314 |
| LMArena Russian | 1289 | 1304 |
| LMArena Spanish | 1248 | 1321 |
Instruction Following o3-mini leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), o3-mini: 75.3 (#67)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1280 | 1338 |
| LiveBench Instruction Following | — | 84.4% |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), o3-mini: 33.8 (#251)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Longer Query | 1301 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Too close to call
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), o3-mini: 50.4 (#177)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | o3-mini |
|---|---|---|
| LMArena Text | 1294 | 1337 |
| LMArena Creative Writing | 1285 | 1286 |
| LMArena Multi-Turn | 1297 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than o3-mini?
DeepSeek-V2.5 (Sep 2024) and o3-mini score almost the same on the Noometry Index (37.0 vs 36.7), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 41.4 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and o3-mini share?
18 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and o3-mini has 51.