Model comparison
DeepSeek-V3 vs GPT-5.1-Codex
DeepSeek-V3 and GPT-5.1-Codex score almost the same on the Noometry Index (39.5 vs 38.6), so choose on price, context window or the category you care about most.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V3 scores higher in 2 categories and GPT-5.1-Codex in 0 categories; one gap is clear of the uncertainty.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 164K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | GPT-5.1-Codex | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.5 | 38.6 |
| Released | 2024-12-26 | 2025-11-12 |
| Weights | Open | Proprietary |
| Context window | 164K | 400K |
| Max output | 164K | 128K |
| Input $ / M tokens | $0.24 | $1.25 |
| Output $ / M tokens | $0.90 | $10 |
| Results tracked | 60 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3: 42.3 (#106), GPT-5.1-Codex: 41.9 (#116)
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | — | 66% |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1337 |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| LMArena Coding | 1368 | — |
| BigCodeBench Complete | 62.2% | — |
| ALE-Bench | — | 1,245 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, GPT-5.1-Codex: 38.0 (#33)
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| METR Time Horizons | 49.6% | 70.8% |
| Terminal-Bench | — | 60.4% |
Reasoning Not comparable
DeepSeek-V3: 20.5 (#236), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| LMArena Hard Prompts | 1365 | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math DeepSeek-V3 leads
DeepSeek-V3: 32.1 (#219), GPT-5.1-Codex: 30.3 (#235)
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 9% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| LMArena Math | 1373 | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Not comparable
DeepSeek-V3: 37.5 (#155), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| LMArena Expert | 1351 | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual Not comparable
DeepSeek-V3: 48.5 (#143), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| LMArena Non-English | 1358 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1385 | — |
| LMArena German | 1374 | — |
| LMArena Japanese | 1333 | — |
| LMArena Korean | 1319 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1358 | — |
Instruction Following Not comparable
DeepSeek-V3: 72.8 (#130), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
| LMArena Instruction Following | 1345 | — |
Long Context Not comparable
DeepSeek-V3: 34.0 (#253), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| Fiction.LiveBench | 50% | — |
| LMArena Longer Query | 1352 | — |
Writing & Preference Not comparable
DeepSeek-V3: 57.4 (#130), GPT-5.1-Codex: —
| Benchmark | DeepSeek-V3 | GPT-5.1-Codex |
|---|---|---|
| LMArena Text | 1375 | — |
| LMArena Creative Writing | 1364 | — |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LMArena Multi-Turn | 1389 | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than GPT-5.1-Codex?
DeepSeek-V3 and GPT-5.1-Codex score almost the same on the Noometry Index (39.5 vs 38.6), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3 or GPT-5.1-Codex?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.
Is DeepSeek-V3 or GPT-5.1-Codex better for coding?
They score almost the same on coding (42.3 vs 41.9); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.1-Codex does, with 400K tokens against 164K.
How many benchmarks do DeepSeek-V3 and GPT-5.1-Codex share?
1 benchmark has published results for both models. DeepSeek-V3 has 60 scored results on Noometry and GPT-5.1-Codex has 6.