Model comparison
DeepSeek LLM 67B vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 49.2 to 24.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GPT-6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Sol leads 72.3 to 31.8.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-6 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.8 | 49.2 |
| Released | 2023-11-29 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 15 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
DeepSeek LLM 67B: 31.3 (#273), GPT-6 Sol: 59.6 (#11)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1096 | 1453 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1692 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GPT-6 Sol: 33.5 (#49)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |
Reasoning GPT-6 Sol leads
DeepSeek LLM 67B: 15.9 (#300), GPT-6 Sol: 49.3 (#34)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1420 |
| NYT Connections (extended) | — | 90.1% |
| Chess Puzzles | 0% | — |
| EBR-Bench | — | 53.3% |
| Epoch Capabilities Index | 110.54 | — |
Math GPT-6 Sol leads
DeepSeek LLM 67B: 8.1 (#318), GPT-6 Sol: 35.8 (#135)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1108 | 1404 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge GPT-6 Sol leads
DeepSeek LLM 67B: 7.1 (#308), GPT-6 Sol: 43.0 (#87)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 6.5% |
| LMArena Expert | — | 1449 |
Multimodal Not comparable
DeepSeek LLM 67B: —, GPT-6 Sol: 47.6 (#9)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
DeepSeek LLM 67B: 29.5 (#262), GPT-6 Sol: 51.0 (#113)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1073 | 1389 |
| LMArena Chinese | 1132 | 1416 |
| LMArena Russian | — | 1407 |
| LMArena Spanish | — | 1377 |
Instruction Following GPT-6 Sol leads
DeepSeek LLM 67B: 55.7 (#272), GPT-6 Sol: 74.4 (#97)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1079 | 1406 |
Long Context GPT-6 Sol leads
DeepSeek LLM 67B: 33.1 (#260), GPT-6 Sol: 43.2 (#100)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1092 | 1415 |
Writing & Preference GPT-6 Sol leads
DeepSeek LLM 67B: 31.8 (#277), GPT-6 Sol: 72.3 (#15)
| Benchmark | DeepSeek LLM 67B | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1105 | 1396 |
| LMArena Creative Writing | 1067 | 1392 |
| LMArena Multi-Turn | 1082 | 1405 |
| EQ-Bench Creative Writing | — | 2125 |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GPT-6 Sol share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-6 Sol has 22.