Model comparison
DeepSeek LLM 67B vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 24.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GPT-5.2 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-5.2 Pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 52.3 |
| Released | 2023-11-29 | 2025-12-11 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $21 |
| Output $ / M tokens | — | $168 |
| Results tracked | 15 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.9 (#278), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning GPT-5.2 Pro leads
DeepSeek LLM 67B: 16.5 (#304), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| Epoch Capabilities Index | 110.5 | 155.4 |
| ARC-AGI-2 | — | 54.2% |
| SimpleBench | — | 57.4% |
| NYT Connections (extended) | — | 79.3% |
| ARC-AGI-1 | — | 90.5% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
Math GPT-5.2 Pro leads
DeepSeek LLM 67B: 8.7 (#324), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
| FrontierMath Tier 4 (v1) | — | 31.3% |
Knowledge Not comparable
DeepSeek LLM 67B: 7.0 (#313), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), GPT-5.2 Pro: —
| Benchmark | DeepSeek LLM 67B | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 24.9 on the Noometry Index.
How many benchmarks do DeepSeek LLM 67B and GPT-5.2 Pro share?
1 benchmark has published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-5.2 Pro has 8.