Model comparison
DeepSeek LLM 67B vs GPT-4o mini
DeepSeek LLM 67B and GPT-4o mini score almost the same on the Noometry Index (24.9 vs 25.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 2 categories and GPT-4o mini in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4o mini leads 42.0 to 29.4.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 52.6% for GPT-4o mini.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | GPT-4o mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 25.5 |
| Released | 2023-11-29 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 15 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), GPT-4o mini: 22.0 (#335)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Coding | 1096 | 1290 |
| Aider Polyglot | — | 3.6% |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GPT-4o mini: 27.5 (#101)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), GPT-4o mini: 8.7 (#347)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | 1267 |
| Epoch Capabilities Index | 110.5 | 126.56 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 54.4% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math GPT-4o mini leads
DeepSeek LLM 67B: 8.7 (#324), GPT-4o mini: 10.4 (#314)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 6.9% |
| LMArena Math | 1108 | 1267 |
| MATH Level 5 | 6.4% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| GSM8K | — | 91.3% |
Knowledge GPT-4o mini leads
DeepSeek LLM 67B: 7.0 (#313), GPT-4o mini: 17.7 (#284)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 24.6% | 37.7% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| LMArena Expert | — | 1235 |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal Not comparable
DeepSeek LLM 67B: —, GPT-4o mini: 25.9 (#122)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual GPT-4o mini leads
DeepSeek LLM 67B: 29.4 (#267), GPT-4o mini: 42.0 (#199)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1073 | 1266 |
| LMArena Chinese | 1132 | 1265 |
| LMArena French | — | 1297 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1216 |
| LMArena Korean | — | 1195 |
| LMArena Russian | — | 1275 |
| LMArena Spanish | — | 1276 |
Instruction Following GPT-4o mini leads
DeepSeek LLM 67B: 55.4 (#277), GPT-4o mini: 61.9 (#239)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1079 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context GPT-4o mini leads
DeepSeek LLM 67B: 33.1 (#265), GPT-4o mini: 39.1 (#186)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1092 | 1289 |
Writing & Preference GPT-4o mini leads
DeepSeek LLM 67B: 31.6 (#282), GPT-4o mini: 39.5 (#248)
| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Text | 1105 | 1286 |
| LMArena Creative Writing | 1067 | 1268 |
| LMArena Multi-Turn | 1082 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is DeepSeek LLM 67B better than GPT-4o mini?
DeepSeek LLM 67B and GPT-4o mini score almost the same on the Noometry Index (24.9 vs 25.5), so choose on price, context window or the category you care about most.
Is DeepSeek LLM 67B or GPT-4o mini better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 22.0 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GPT-4o mini share?
15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-4o mini has 60.