Model comparison
DeepSeek LLM 67B vs GPT-5.3 Chat
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 24.9 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-5.3 Chat in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.3 Chat leads 38.8 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-5.3 Chat | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 42.8 |
| Released | 2023-11-29 | 2026-03-03 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
DeepSeek LLM 67B: 31.9 (#278), GPT-5.3 Chat: 41.4 (#124)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Coding | 1096 | 1408 |
Reasoning GPT-5.3 Chat leads
DeepSeek LLM 67B: 16.5 (#304), GPT-5.3 Chat: 28.5 (#102)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1399 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math GPT-5.3 Chat leads
DeepSeek LLM 67B: 8.7 (#324), GPT-5.3 Chat: 38.2 (#142)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Math | 1108 | 1389 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge GPT-5.3 Chat leads
DeepSeek LLM 67B: 7.0 (#313), GPT-5.3 Chat: 38.8 (#140)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1397 |
Multilingual GPT-5.3 Chat leads
DeepSeek LLM 67B: 29.4 (#267), GPT-5.3 Chat: 50.3 (#124)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Non-English | 1073 | 1382 |
| LMArena Chinese | 1132 | 1432 |
| LMArena French | — | 1397 |
| LMArena German | — | 1384 |
| LMArena Japanese | — | 1352 |
| LMArena Korean | — | 1346 |
| LMArena Russian | — | 1400 |
| LMArena Spanish | — | 1371 |
Instruction Following GPT-5.3 Chat leads
DeepSeek LLM 67B: 55.4 (#277), GPT-5.3 Chat: 72.8 (#129)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Instruction Following | 1079 | 1378 |
Long Context GPT-5.3 Chat leads
DeepSeek LLM 67B: 33.1 (#265), GPT-5.3 Chat: 42.6 (#120)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Longer Query | 1092 | 1396 |
Writing & Preference GPT-5.3 Chat leads
DeepSeek LLM 67B: 31.6 (#282), GPT-5.3 Chat: 63.1 (#68)
| Benchmark | DeepSeek LLM 67B | GPT-5.3 Chat |
|---|---|---|
| LMArena Text | 1105 | 1389 |
| LMArena Creative Writing | 1067 | 1355 |
| LMArena Multi-Turn | 1082 | 1412 |
| EQ-Bench Creative Writing | — | 1690 |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-5.3 Chat?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or GPT-5.3 Chat better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GPT-5.3 Chat share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-5.3 Chat has 18.