Model comparison
DeepSeek LLM 67B vs GPT-6.1 Sol
DeepSeek LLM 67B has enough public results to be ranked (#341); GPT-6.1 Sol does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in coding, where GPT-6.1 Sol leads 51.4 to 31.3.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-6.1 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.8 | 42.1 |
| Released | 2023-11-29 | 2026-09-29 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 15 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
DeepSeek LLM 67B: 31.3 (#273), GPT-6.1 Sol: 51.4
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | — | 75.2% |
| LMArena Coding | 1096 | — |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GPT-6.1 Sol: 34.3
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| GDP.pdf | — | 32% |
Reasoning Not comparable
DeepSeek LLM 67B: 15.9 (#300), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.54 | — |
Math Not comparable
DeepSeek LLM 67B: 8.1 (#318), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Not comparable
DeepSeek LLM 67B: 7.1 (#308), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual Not comparable
DeepSeek LLM 67B: 29.5 (#262), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.7 (#272), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#260), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.8 (#277), GPT-6.1 Sol: —
| Benchmark | DeepSeek LLM 67B | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-6.1 Sol?
DeepSeek LLM 67B has enough public results to be ranked (#341); GPT-6.1 Sol does not yet, so treat this comparison as directional.
Is DeepSeek LLM 67B or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 51.4 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GPT-6.1 Sol share?
0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-6.1 Sol has 2.