Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs GPT-3.5-turbo
GPT-3.5-turbo has enough public results to be ranked (#350); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
DeepSeekSummary
- They share 8 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and GPT-3.5-turbo in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 23.9.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.9% for DeepSeek-V2 (MoE-236B, May 2024) and 39.1% for GPT-3.5-turbo.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 40.3 | 23.2 |
| Released | 2024-05-07 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | — | 16K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 10 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 39.1% |
| BigCodeBench Complete | 59.4% | 50.6% |
| WeirdML | — | 3.5% |
| LMArena Coding | — | 1136 |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| METR Time Horizons | — | 21.5% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 13.8 (#332)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| BIG-Bench Hard | 78.8% | 61.6% |
| Epoch Capabilities Index | 124.77 | 118.55 |
| WinoGrande | 86.3% | 81.6% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1108 |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 6.3 (#327)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| LMArena Math | — | 1142 |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 10.0 (#303)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 87.4% |
| MMLU | 78.4% | 71.4% |
| TriviaQA | 80% | 85.8% |
| GPQA Diamond | — | 28% |
| LMArena Expert | — | 1070 |
| BoolQ | — | 87% |
| OpenBookQA | — | 86% |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 31.5 (#258)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | — | 1108 |
| LMArena Chinese | — | 1075 |
| LMArena French | — | 1118 |
| LMArena German | — | 1090 |
| LMArena Japanese | — | 1043 |
| LMArena Korean | — | 1019 |
| LMArena Russian | — | 1123 |
| LMArena Spanish | — | 1121 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 57.9 (#262)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | — | 1119 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 34.0 (#254)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | — | 1121 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, GPT-3.5-turbo: 25.3 (#305)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | — | 1125 |
| LMArena Creative Writing | — | 1092 |
| EQ-Bench Creative Writing | — | 451 |
| LMArena Multi-Turn | — | 1117 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than GPT-3.5-turbo?
GPT-3.5-turbo has enough public results to be ranked (#350); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or GPT-3.5-turbo better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 23.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GPT-3.5-turbo share?
8 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GPT-3.5-turbo has 44.