Model comparison
DeepSeek-V2.5 (Sep 2024) vs GPT-5.5 Instant
GPT-5.5 Instant is the stronger model overall, scoring 42.7 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 2 categories and GPT-5.5 Instant in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 34.8.
- 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 Instant | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.6 | 42.7 |
| Released | 2024-09-06 | 2026-05-05 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), GPT-5.5 Instant: 44.3 (#74)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Coding | 1309 | 1433 |
| Aider Polyglot | 17.8% | — |
| SciCode | — | 48.6% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), GPT-5.5 Instant: 24.9 (#155)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1426 |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Epoch Capabilities Index | — | 142.52 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), GPT-5.5 Instant: 26.5 (#259)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Math | 1288 | 1420 |
| FrontierMath (Tiers 1-3) | — | 26.3% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 68.1% |
Knowledge GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), GPT-5.5 Instant: 48.9 (#74)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Expert | 1266 | 1409 |
| GPQA Diamond | — | 82.5% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, GPT-5.5 Instant: 40.0 (#52)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Vision | — | 1250 |
| LMArena Document | — | 1403 |
Multilingual GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), GPT-5.5 Instant: 52.8 (#80)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Non-English | 1273 | 1417 |
| LMArena Chinese | 1318 | 1456 |
| LMArena French | 1289 | 1428 |
| LMArena German | 1258 | 1411 |
| LMArena Japanese | 1228 | 1408 |
| LMArena Korean | 1209 | 1392 |
| LMArena Russian | 1289 | 1431 |
| LMArena Spanish | 1248 | 1429 |
Instruction Following GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), GPT-5.5 Instant: 74.2 (#100)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1280 | 1406 |
Long Context GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), GPT-5.5 Instant: 43.4 (#96)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Longer Query | 1301 | 1422 |
Writing & Preference GPT-5.5 Instant leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), GPT-5.5 Instant: 61.8 (#85)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-5.5 Instant |
|---|---|---|
| LMArena Text | 1294 | 1419 |
| LMArena Creative Writing | 1285 | 1419 |
| LMArena Multi-Turn | 1297 | 1433 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GPT-5.5 Instant?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GPT-5.5 Instant better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GPT-5.5 Instant share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GPT-5.5 Instant has 27.