Model comparison
DeepSeek V4 Pro vs GPT-6 Sol
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 49.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 6 categories and GPT-6 Sol in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 35.8.
- The biggest single-benchmark swing is FrontierCode: 28.6% for DeepSeek V4 Pro and 49.3% for GPT-6 Sol.
- DeepSeek V4 Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | GPT-6 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 54.2 | 49.2 |
| Released | 2026-04-24 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 128K |
| Input $ / M tokens | $0.43 | $2 |
| Output $ / M tokens | $0.87 | $10 |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
DeepSeek V4 Pro: 52.2 (#31), GPT-6 Sol: 59.6 (#11)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| FrontierCode | 28.6% | 49.3% |
| LMArena WebDev | 1582 | 1692 |
| LMArena Coding | 1470 | 1453 |
| SWE-bench Verified | 77.6% | — |
| DeepSWE | — | 68.8% |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Too close to call
DeepSeek V4 Pro: 32.7 (#54), GPT-6 Sol: 33.5 (#49)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 47.3% | — |
| GDP.pdf | — | 28% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.4 (#22), GPT-6 Sol: 49.3 (#34)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| NYT Connections (extended) | 91.3% | 90.1% |
| LMArena Hard Prompts | 1461 | 1420 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.39 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.6 (#24), GPT-6 Sol: 35.8 (#135)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1455 | 1404 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#28), GPT-6 Sol: 43.0 (#87)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 8.6% | 6.5% |
| LMArena Expert | 1463 | 1449 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, GPT-6 Sol: 47.6 (#9)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.5 (#44), GPT-6 Sol: 51.0 (#113)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1438 | 1389 |
| LMArena Chinese | 1486 | 1416 |
| LMArena Russian | 1452 | 1407 |
| LMArena Spanish | 1457 | 1377 |
| LMArena French | 1473 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1448 | — |
| LMArena Korean | 1452 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.3 (#44), GPT-6 Sol: 74.4 (#97)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1448 | 1406 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#49), GPT-6 Sol: 43.2 (#100)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1459 | 1415 |
| CL-bench Life | 13.5% | — |
Writing & Preference GPT-6 Sol leads
DeepSeek V4 Pro: 65.6 (#45), GPT-6 Sol: 72.3 (#15)
| Benchmark | DeepSeek V4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1451 | 1396 |
| LMArena Creative Writing | 1446 | 1392 |
| EQ-Bench Creative Writing | 1553 | 2125 |
| LMArena Multi-Turn | 1467 | 1405 |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than GPT-6 Sol?
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 49.2 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or GPT-6 Sol?
DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is DeepSeek V4 Pro or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 52.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and GPT-6 Sol share?
18 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and GPT-6 Sol has 22.