Model comparison
DeepSeek LLM 67B vs GPT-6 Astra
GPT-6 Astra is the stronger model overall, scoring 70.3 to 24.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GPT-6 Astra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Astra leads 93.4 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 100% for GPT-6 Astra.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-6 Astra | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.8 | 70.3 |
| Released | 2023-11-29 | 2026-09-03 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $10 |
| Output $ / M tokens | — | $50 |
| Results tracked | 15 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Astra leads
DeepSeek LLM 67B: 31.3 (#273), GPT-6 Astra: 70.5 (#3)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Coding | 1096 | 1488 |
| DeepSWE | — | 74.1% |
| FrontierCode | — | 53.3% |
| LMArena WebDev | — | 1792 |
| FrontierSWE | — | 65.5% |
| SciCode | — | 56.5% |
| WeirdML | — | 93.6% |
| MirrorCode | — | 46.7% |
| ALE-Bench | — | 2,951 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GPT-6 Astra: 52.3 (#3)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| APEX-Agents | — | 64.7% |
| Remote Labor Index | — | 20.8% |
| BALROG | — | 68.3% |
| Vending-Bench 2 | — | 15,515 |
Reasoning GPT-6 Astra leads
DeepSeek LLM 67B: 15.9 (#300), GPT-6 Astra: 85.1 (#1)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| Chess Puzzles | 0% | 72% |
| LMArena Hard Prompts | 1070 | 1464 |
| Epoch Capabilities Index | 110.54 | 166.6 |
| ARC-AGI-2 | — | 95% |
| NYT Connections (extended) | — | 98.1% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| EBR-Bench | — | 76.2% |
| Mystery Game Puzzles | — | 84% |
| DTBench | — | 97.3% |
| LMCA | — | 64.4% |
| Bench to the Future 3 | — | 0.14 |
Math GPT-6 Astra leads
DeepSeek LLM 67B: 8.1 (#318), GPT-6 Astra: 93.4 (#1)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 100% |
| LMArena Math | 1108 | 1463 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 97.6% |
| ProofBench | — | 99% |
| MATH Level 5 | 6.4% | — |
| FrontierMath Erdős | — | 2.9% |
Knowledge GPT-6 Astra leads
DeepSeek LLM 67B: 7.1 (#308), GPT-6 Astra: 75.3 (#1)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| GPQA Diamond | 24.6% | 95.8% |
| Humanity's Last Exam | — | 54.8% |
| SimpleQA Verified | — | 75.6% |
| Vectara Hallucination Rate | — | 8.7% |
| LMArena Expert | — | 1486 |
Multimodal Not comparable
DeepSeek LLM 67B: —, GPT-6 Astra: 55.1 (#3)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Vision | — | 1280 |
| Blueprint-Bench 2 | — | 49.7% |
| Furniture Assembly | — | 80% |
| LMArena Document | — | 1468 |
Multilingual GPT-6 Astra leads
DeepSeek LLM 67B: 29.5 (#262), GPT-6 Astra: 54.0 (#53)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Non-English | 1073 | 1431 |
| LMArena Chinese | 1132 | 1495 |
| LMArena French | — | 1467 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1412 |
Instruction Following GPT-6 Astra leads
DeepSeek LLM 67B: 55.7 (#272), GPT-6 Astra: 76.6 (#37)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Instruction Following | 1079 | 1454 |
Long Context GPT-6 Astra leads
DeepSeek LLM 67B: 33.1 (#260), GPT-6 Astra: 44.7 (#57)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Longer Query | 1092 | 1460 |
Writing & Preference GPT-6 Astra leads
DeepSeek LLM 67B: 31.8 (#277), GPT-6 Astra: 75.7 (#7)
| Benchmark | DeepSeek LLM 67B | GPT-6 Astra |
|---|---|---|
| LMArena Text | 1105 | 1443 |
| LMArena Creative Writing | 1067 | 1423 |
| LMArena Multi-Turn | 1082 | 1457 |
| EQ-Bench Creative Writing | — | 2173 |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-6 Astra?
GPT-6 Astra is the stronger model overall, scoring 70.3 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or GPT-6 Astra better for coding?
GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GPT-6 Astra share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-6 Astra has 51.