# DeepSeek-V3.1-Terminus vs o4-mini

> DeepSeek-V3.1-Terminus and o4-mini score almost the same on the Noometry Index (42.6 vs 41.6), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-o4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 3 categories and o4-mini in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 54.2.
- 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 $0.30 / $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.

## Snapshot

| | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 41.6 |
| Rank | 96 | 119 |
| Context | 164K | 200K |
| Input $/M | $0.30 | $1.10 |
| Output $/M | $1 | $4.40 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- o4-mini: 41.6 (#110)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Coding | 1426 | 1369 |
| 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

- DeepSeek-V3.1-Terminus: —
- o4-mini: 32.3 (#57)

| 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: 25.7 (#126)
- o4-mini: 24.6 (#143)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 67.6% |
| CritPt | 1.7% | 0.6% |
| LMArena Hard Prompts | 1427 | 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 | — | 145.63 |
| ForecastBench | — | 61.8 |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- o4-mini: 40.2 (#79)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Math | 1402 | 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

- DeepSeek-V3.1-Terminus: —
- o4-mini: 43.5 (#83)

| 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 | — | 1344 |

## Multimodal

- DeepSeek-V3.1-Terminus: —
- o4-mini: 39.5 (#46)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- o4-mini: 47.2 (#149)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Non-English | 1407 | 1336 |
| LMArena Russian | 1434 | 1334 |
| LMArena Chinese | — | 1355 |
| LMArena French | — | 1362 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- o4-mini: 75.4 (#63)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1406 | 1321 |
| IFEval | — | 92.8% |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- o4-mini: 45.5 (#31)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Longer Query | 1426 | 1315 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- o4-mini: 54.2 (#148)

| Benchmark | DeepSeek-V3.1-Terminus | o4-mini |
|---|---|---|
| LMArena Text | 1420 | 1353 |
| LMArena Creative Writing | 1404 | 1294 |
| LMArena Multi-Turn | 1411 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |

## FAQ

### Is DeepSeek-V3.1-Terminus better than o4-mini?

DeepSeek-V3.1-Terminus and o4-mini score almost the same on the Noometry Index (42.6 vs 41.6), so choose on price, context window or the category you care about most.

### Which is cheaper, DeepSeek-V3.1-Terminus or o4-mini?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 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?

They score almost the same on coding (41.5 vs 41.6); test both on your own repository before choosing.

### 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.