Model comparison
DeepSeek-V2.5 (Sep 2024) vs GPT-5.5 Pro
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 37.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in math, where GPT-5.5 Pro leads 83.8 to 33.3.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.0 | 64.3 |
| Released | 2024-09-06 | 2026-04-23 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $180 |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), GPT-5.5 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1310 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning GPT-5.5 Pro leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), GPT-5.5 Pro: 73.6 (#7)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| ARC-AGI-2 | — | 84.6% |
| SimpleBench | — | 76.9% |
| ARC-AGI-1 | — | 96.5% |
| CritPt | — | 30.6% |
| Chess Puzzles | — | 64% |
| LMArena Hard Prompts | 1289 | — |
| DTBench | — | 96% |
| LMCA | — | 53.9% |
| Epoch Capabilities Index | — | 162.45 |
Math GPT-5.5 Pro leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), GPT-5.5 Pro: 83.8 (#8)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 87.7% |
| FrontierMath Tier 4 | — | 78% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| LMArena Math | 1289 | — |
| FrontierMath (Feb 2025 set) | — | 52.4% |
| FrontierMath Tier 4 (v1) | — | 39.6% |
Knowledge GPT-5.5 Pro leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), GPT-5.5 Pro: 64.2 (#17)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | — | 93.9% |
| LMArena Expert | 1266 | — |
Multilingual Not comparable
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), GPT-5.5 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1317 | — |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Not comparable
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), GPT-5.5 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1280 | — |
Long Context Not comparable
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), GPT-5.5 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| LMArena Longer Query | 1301 | — |
Writing & Preference Not comparable
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), GPT-5.5 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Pro |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GPT-5.5 Pro?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 37.0 on the Noometry Index.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GPT-5.5 Pro share?
0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GPT-5.5 Pro has 14.