Model comparison
DeepSeek-V3 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.5 on the Noometry Index. DeepSeek-V3 costs 9.9× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
DeepSeekSummary
- They share 26 benchmarks with published results for both. DeepSeek-V3 scores higher in 0 categories and GPT-6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 32.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 100% for GPT-6 Sol.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | GPT-6 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.5 | 61.8 |
| Released | 2024-12-26 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 164K | 128K |
| Input $ / M tokens | $0.24 | $2 |
| Output $ / M tokens | $0.90 | $10 |
| Results tracked | 60 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
DeepSeek-V3: 42.3 (#106), GPT-6 Sol: 60.1 (#11)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| SciCode | 35.8% | 57.6% |
| LMArena Coding | 1368 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1688 |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| ALE-Bench | — | 2,462 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, GPT-6 Sol: 37.2 (#36)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| METR Time Horizons | 49.6% | — |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
DeepSeek-V3: 20.5 (#236), GPT-6 Sol: 74.0 (#9)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| CritPt | 0% | 30.9% |
| LMArena Hard Prompts | 1365 | 1418 |
| DTBench | 64.8% | 97.3% |
| LMCA | 15.5% | 59.1% |
| Epoch Capabilities Index | 135.94 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 65.8% | — |
| Mystery Game Puzzles | — | 56% |
| LiveBench Data Analysis | 60.9% | — |
| BIG-Bench Hard | 87.5% | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math GPT-6 Sol leads
DeepSeek-V3: 32.1 (#219), GPT-6 Sol: 87.2 (#7)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 100% |
| LMArena Math | 1373 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge GPT-6 Sol leads
DeepSeek-V3: 37.5 (#155), GPT-6 Sol: 64.8 (#15)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 67.6% | 94.3% |
| Vectara Hallucination Rate | 6.1% | 6.5% |
| LMArena Expert | 1351 | 1439 |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multimodal Not comparable
DeepSeek-V3: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
DeepSeek-V3: 48.5 (#143), GPT-6 Sol: 50.5 (#118)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1358 | 1385 |
| LMArena Chinese | 1391 | 1405 |
| LMArena French | 1385 | 1410 |
| LMArena German | 1374 | 1390 |
| LMArena Japanese | 1333 | 1385 |
| LMArena Korean | 1319 | 1341 |
| LMArena Russian | 1373 | 1401 |
| LMArena Spanish | 1358 | 1384 |
Instruction Following GPT-6 Sol leads
DeepSeek-V3: 72.8 (#130), GPT-6 Sol: 74.5 (#94)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1345 | 1412 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context GPT-6 Sol leads
DeepSeek-V3: 34.0 (#253), GPT-6 Sol: 43.1 (#108)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1352 | 1411 |
| Fiction.LiveBench | 50% | — |
Writing & Preference GPT-6 Sol leads
DeepSeek-V3: 57.4 (#130), GPT-6 Sol: 71.9 (#18)
| Benchmark | DeepSeek-V3 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1375 | 1395 |
| LMArena Creative Writing | 1364 | 1378 |
| EQ-Bench Creative Writing | 1472 | 2125 |
| LMArena Multi-Turn | 1389 | 1412 |
| Short-Story Creative Writing | 77% | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.5 on the Noometry Index. DeepSeek-V3 costs 9.9× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3 or GPT-6 Sol?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is DeepSeek-V3 or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3 and GPT-6 Sol share?
26 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and GPT-6 Sol has 45.