Model comparison
DeepSeek-V2.5 (Sep 2024) vs gpt-oss-120b
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 36.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 3 categories and gpt-oss-120b in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 35.9.
- The biggest single-benchmark swing is Aider Polyglot: 17.8% for DeepSeek-V2.5 (Sep 2024) and 41.8% for gpt-oss-120b.
Side by side
| DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.6 | 36.3 |
| Released | 2024-09-06 | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 22 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), gpt-oss-120b: 33.5 (#256)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| Aider Polyglot | 17.8% | 41.8% |
| LMArena Coding | 1309 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, gpt-oss-120b: 12.2 (#153)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), gpt-oss-120b: 20.0 (#245)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1364 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.93 |
Math gpt-oss-120b leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), gpt-oss-120b: 52.5 (#50)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1288 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |
Knowledge gpt-oss-120b leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), gpt-oss-120b: 42.4 (#96)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Expert | 1266 | 1356 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multilingual gpt-oss-120b leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), gpt-oss-120b: 48.0 (#147)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1273 | 1351 |
| LMArena Chinese | 1318 | 1385 |
| LMArena French | 1289 | 1369 |
| LMArena German | 1258 | 1353 |
| LMArena Japanese | 1228 | 1331 |
| LMArena Korean | 1209 | 1282 |
| LMArena Russian | 1289 | 1343 |
| LMArena Spanish | 1248 | 1389 |
Instruction Following gpt-oss-120b leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), gpt-oss-120b: 69.3 (#173)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1280 | 1318 |
| IFEval | — | 83.6% |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), gpt-oss-120b: 31.4 (#278)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1301 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), gpt-oss-120b: 46.5 (#217)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1294 | 1365 |
| LMArena Creative Writing | 1285 | 1275 |
| LMArena Multi-Turn | 1297 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than gpt-oss-120b?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 36.3 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and gpt-oss-120b share?
18 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and gpt-oss-120b has 48.