Model comparison
DeepSeek-V3.1-Terminus vs o3-pro
DeepSeek-V3.1-Terminus and o3-pro score almost the same on the Noometry Index (42.6 vs 42.7), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and o3-pro in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 43.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 72.1% for o3-pro.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro 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 | o3-pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 42.7 |
| Released | 2025-09-22 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.30 | $20 |
| Output $ / M tokens | $1 | $80 |
| Results tracked | 16 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
DeepSeek-V3.1-Terminus: 41.5 (#114), o3-pro: 55.1 (#22)
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| SciCode | 40.6% | — |
| WeirdML | — | 58.2% |
| LMArena Coding | 1426 | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), o3-pro: 24.1 (#152)
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 72.1% |
| DTBench | 81.3% | 86.9% |
| LMCA | 28.6% | 38.5% |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 1.7% | — |
| LMArena Hard Prompts | 1427 | — |
| Epoch Capabilities Index | — | 147.43 |
Math Not comparable
DeepSeek-V3.1-Terminus: 35.7 (#138), o3-pro: —
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| LMArena Math | 1402 | — |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, o3-pro: 29.0 (#234)
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Multilingual Not comparable
DeepSeek-V3.1-Terminus: 52.3 (#87), o3-pro: —
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1434 | — |
Instruction Following Not comparable
DeepSeek-V3.1-Terminus: 74.4 (#96), o3-pro: —
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1406 | — |
Long Context o3-pro leads
DeepSeek-V3.1-Terminus: 43.5 (#88), o3-pro: 72.1 (#1)
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1426 | — |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), o3-pro: 57.1 (#128)
| Benchmark | DeepSeek-V3.1-Terminus | o3-pro |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1404 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than o3-pro?
DeepSeek-V3.1-Terminus and o3-pro score almost the same on the Noometry Index (42.6 vs 42.7), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1-Terminus or o3-pro?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; o3-pro lists at $20 and $80.
Is DeepSeek-V3.1-Terminus or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 41.5 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and o3-pro share?
3 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and o3-pro has 12.