Model comparison
DeepSeek V4.1 Flash vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 15× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
DeepSeekSummary
- They share 36 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 3 categories and GPT-6 Sol in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 50.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 26.8% for DeepSeek V4.1 Flash and 90% for GPT-6 Sol.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | GPT-6 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 52.8 | 61.8 |
| Released | 2026-09-09 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 128K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.60 | $10 |
| Results tracked | 37 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
DeepSeek V4.1 Flash: 52.9 (#32), GPT-6 Sol: 60.1 (#11)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1619 | 1688 |
| SciCode | 51.9% | 57.6% |
| LMArena Coding | 1506 | 1447 |
| ALE-Bench | 1,092 | 2,462 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
Agentic & Tool Use GPT-6 Sol leads
DeepSeek V4.1 Flash: 31.2 (#69), GPT-6 Sol: 37.2 (#36)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 39.5% | 54.3% |
| GDP.pdf | 19.8% | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
DeepSeek V4.1 Flash: 50.2 (#36), GPT-6 Sol: 74.0 (#9)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| NYT Connections (extended) | 89.6% | 90.1% |
| CritPt | 14.3% | 30.9% |
| LMArena Hard Prompts | 1483 | 1418 |
| Mystery Game Puzzles | 43% | 56% |
| DTBench | 89.9% | 97.3% |
| LMCA | 47% | 59.1% |
| Epoch Capabilities Index | 154.9 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| ARC-AGI-1 | — | 95.5% |
| EBR-Bench | — | 53.3% |
| Surface Evolver Bench | 46.3% | — |
Math GPT-6 Sol leads
DeepSeek V4.1 Flash: 66.7 (#25), GPT-6 Sol: 87.2 (#7)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 89.8% |
| FrontierMath Tier 4 | 26.8% | 90% |
| OTIS Mock AIME 2024-2025 | 98.3% | 100% |
| ProofBench | 54% | 83% |
| LMArena Math | 1477 | 1402 |
Knowledge GPT-6 Sol leads
DeepSeek V4.1 Flash: 57.9 (#38), GPT-6 Sol: 64.8 (#15)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 89.8% | 94.3% |
| LMArena Expert | 1506 | 1439 |
| SimpleQA Verified | — | 60.7% |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal GPT-6 Sol leads
DeepSeek V4.1 Flash: 39.1 (#61), GPT-6 Sol: 47.6 (#10)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1277 | 1245 |
| Furniture Assembly | 34.2% | 58.3% |
| Blueprint-Bench 2 | — | 36.9% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), GPT-6 Sol: 50.5 (#118)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1448 | 1385 |
| LMArena Chinese | 1497 | 1405 |
| LMArena French | 1452 | 1410 |
| LMArena German | 1484 | 1390 |
| LMArena Japanese | 1412 | 1385 |
| LMArena Korean | 1452 | 1341 |
| LMArena Russian | 1471 | 1401 |
| LMArena Spanish | 1459 | 1384 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), GPT-6 Sol: 74.5 (#94)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1474 | 1412 |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), GPT-6 Sol: 43.1 (#108)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1475 | 1411 |
Writing & Preference GPT-6 Sol leads
DeepSeek V4.1 Flash: 65.4 (#48), GPT-6 Sol: 71.9 (#18)
| Benchmark | DeepSeek V4.1 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1462 | 1395 |
| LMArena Creative Writing | 1435 | 1378 |
| EQ-Bench Creative Writing | 1540 | 2125 |
| LMArena Multi-Turn | 1457 | 1412 |
Frequently asked questions
Is DeepSeek V4.1 Flash better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 15× 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 V4.1 Flash or GPT-6 Sol?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is DeepSeek V4.1 Flash or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 52.9 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 V4.1 Flash and GPT-6 Sol share?
36 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GPT-6 Sol has 45.