Model comparison
DeepSeek-V2.5 (Sep 2024) vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GPT-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5.1 leads 83.9 to 67.5.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GPT-5.1 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.6 | 49.0 |
| Released | 2024-09-06 | 2025-11-13 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 22 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), GPT-5.1: 46.4 (#66)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Coding | 1309 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
| BigCodeBench Instruct | 48.6% | — |
| LiveBench Coding | — | 72.5% |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,192 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, GPT-5.1: 32.7 (#60)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), GPT-5.1: 39.8 (#58)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1457 |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| Chess Puzzles | — | 32% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | — | 72.1% |
| LMCA | — | 43.9% |
| Epoch Capabilities Index | — | 149.64 |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), GPT-5.1: 52.2 (#51)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Math | 1288 | 1447 |
| OTIS Mock AIME 2024-2025 | — | 88.6% |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), GPT-5.1: 50.6 (#71)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Expert | 1266 | 1470 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, GPT-5.1: 44.8 (#19)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Vision | — | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), GPT-5.1: 53.8 (#56)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1273 | 1431 |
| LMArena Chinese | 1318 | 1495 |
| LMArena French | 1289 | 1450 |
| LMArena German | 1258 | 1438 |
| LMArena Japanese | 1228 | 1453 |
| LMArena Korean | 1209 | 1401 |
| LMArena Russian | 1289 | 1435 |
| LMArena Spanish | 1248 | 1433 |
Instruction Following GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), GPT-5.1: 83.9 (#1)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), GPT-5.1: 47.6 (#14)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1301 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), GPT-5.1: 64.5 (#55)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.1 |
|---|---|---|
| LMArena Text | 1294 | 1443 |
| LMArena Creative Writing | 1285 | 1427 |
| LMArena Multi-Turn | 1297 | 1450 |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GPT-5.1 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GPT-5.1 has 63.