Model comparison
DeepSeek-V3 vs GPT-5.5 Instant
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 39.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek-V3 scores higher in 1 category and GPT-5.5 Instant in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 37.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 68.1% for GPT-5.5 Instant.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | GPT-5.5 Instant | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.5 | 42.7 |
| Released | 2024-12-26 | 2026-05-05 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 164K | — |
| Input $ / M tokens | $0.24 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
DeepSeek-V3: 42.3 (#106), GPT-5.5 Instant: 44.3 (#74)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| SciCode | 35.8% | 48.6% |
| LMArena Coding | 1368 | 1433 |
| Aider Polyglot | 55.1% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, GPT-5.5 Instant: —
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning GPT-5.5 Instant leads
DeepSeek-V3: 20.5 (#236), GPT-5.5 Instant: 24.9 (#155)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1365 | 1426 |
| Epoch Capabilities Index | 135.94 | 142.52 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| 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-5.5 Instant: 26.5 (#259)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 68.1% |
| LMArena Math | 1373 | 1420 |
| FrontierMath (Tiers 1-3) | — | 26.3% |
| FrontierMath Tier 4 | — | 2.4% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge GPT-5.5 Instant leads
DeepSeek-V3: 37.5 (#155), GPT-5.5 Instant: 48.9 (#74)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| GPQA Diamond | 67.6% | 82.5% |
| LMArena Expert | 1351 | 1409 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multimodal Not comparable
DeepSeek-V3: —, GPT-5.5 Instant: 40.0 (#52)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| LMArena Vision | — | 1250 |
| LMArena Document | — | 1403 |
Multilingual GPT-5.5 Instant leads
DeepSeek-V3: 48.5 (#143), GPT-5.5 Instant: 52.8 (#80)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| LMArena Non-English | 1358 | 1417 |
| LMArena Chinese | 1391 | 1456 |
| LMArena French | 1385 | 1428 |
| LMArena German | 1374 | 1411 |
| LMArena Japanese | 1333 | 1408 |
| LMArena Korean | 1319 | 1392 |
| LMArena Russian | 1373 | 1431 |
| LMArena Spanish | 1358 | 1429 |
Instruction Following GPT-5.5 Instant leads
DeepSeek-V3: 72.8 (#130), GPT-5.5 Instant: 74.2 (#100)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1345 | 1406 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context GPT-5.5 Instant leads
DeepSeek-V3: 34.0 (#253), GPT-5.5 Instant: 43.4 (#96)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| LMArena Longer Query | 1352 | 1422 |
| Fiction.LiveBench | 50% | — |
Writing & Preference GPT-5.5 Instant leads
DeepSeek-V3: 57.4 (#130), GPT-5.5 Instant: 61.8 (#85)
| Benchmark | DeepSeek-V3 | GPT-5.5 Instant |
|---|---|---|
| LMArena Text | 1375 | 1419 |
| LMArena Creative Writing | 1364 | 1419 |
| LMArena Multi-Turn | 1389 | 1433 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than GPT-5.5 Instant?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 39.5 on the Noometry Index.
Is DeepSeek-V3 or GPT-5.5 Instant better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 42.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V3 and GPT-5.5 Instant share?
22 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and GPT-5.5 Instant has 27.