Model comparison
DeepSeek-V3.1-Terminus vs o3
o3 is the stronger model overall, scoring 47.5 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 7.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and o3 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 50.2 to 38.5.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 39.7% for o3.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $2 / $8 for o3.
- o3 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 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 47.5 |
| Released | 2025-09-22 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 147K | 100K |
| Input $ / M tokens | $0.27 | $2 |
| Output $ / M tokens | $1 | $8 |
| Results tracked | 16 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
DeepSeek-V3.1-Terminus: 42.0 (#113), o3: 46.8 (#64)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Coding | 1426 | 1408 |
| ALE-Bench | 745.17 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 40.6% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, o3: 34.5 (#44)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
DeepSeek-V3.1-Terminus: 26.4 (#133), o3: 32.0 (#78)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 67.6% |
| CritPt | 1.7% | 1.4% |
| LMArena Hard Prompts | 1426 | 1402 |
| DTBench | 81.3% | 84.8% |
| LMCA | 28.6% | 39.7% |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
DeepSeek-V3.1-Terminus: 38.5 (#137), o3: 50.2 (#58)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Math | 1402 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, o3: 54.6 (#52)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, o3: 41.4 (#36)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Too close to call
DeepSeek-V3.1-Terminus: 52.1 (#92), o3: 51.7 (#105)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Non-English | 1407 | 1401 |
| LMArena Russian | 1436 | 1406 |
| LMArena Chinese | — | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Spanish | — | 1395 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), o3: 72.8 (#127)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
DeepSeek-V3.1-Terminus: 43.4 (#97), o3: 53.3 (#6)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Longer Query | 1421 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
DeepSeek-V3.1-Terminus: 61.0 (#92), o3: 63.5 (#64)
| Benchmark | DeepSeek-V3.1-Terminus | o3 |
|---|---|---|
| LMArena Text | 1419 | 1410 |
| LMArena Creative Writing | 1403 | 1359 |
| LMArena Multi-Turn | 1411 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than o3?
o3 is the stronger model overall, scoring 47.5 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 7.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or o3?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; o3 lists at $2 and $8.
Is DeepSeek-V3.1-Terminus or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and o3 share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and o3 has 63.