Model comparison
DeepSeek LLM 67B vs Gemini 1.5 Pro (May 2024)
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
GoogleSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Gemini 1.5 Pro (May 2024) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 1.5 Pro (May 2024) leads 29.4 to 7.0.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 70.4% for Gemini 1.5 Pro (May 2024).
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 32.1 |
| Released | 2023-11-29 | 2024-02-15 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 31.9 (#278), Gemini 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Coding | 1096 | 1294 |
| WeirdML | — | 22.2% |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1296 |
| Epoch Capabilities Index | 110.5 | 131.73 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 27.1% |
| Chess Puzzles | 0% | — |
| DTBench | — | 59% |
| BIG-Bench Hard | — | 89.2% |
| ForecastBench | — | 58.4 |
Math Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 8.7 (#324), Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 23.1% |
| LMArena Math | 1108 | 1315 |
| MATH Level 5 | 6.4% | 70.4% |
| Omni-MATH | — | 36.4% |
Knowledge Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 7.0 (#313), Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 24.6% | 57.2% |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| GPQA (HELM) | — | 53.4% |
| LMArena Expert | — | 1279 |
| MMLU | — | 86.9% |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
Multilingual Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 29.4 (#267), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1073 | 1312 |
| LMArena Chinese | 1132 | 1331 |
| LMArena French | — | 1302 |
| LMArena German | — | 1286 |
| LMArena Japanese | — | 1292 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1320 |
| LMArena Spanish | — | 1311 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 55.4 (#277), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1079 | 1297 |
| IFEval | — | 83.7% |
Long Context Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 33.1 (#265), Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1092 | 1308 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
DeepSeek LLM 67B: 31.6 (#282), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | DeepSeek LLM 67B | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1105 | 1319 |
| LMArena Creative Writing | 1067 | 1333 |
| LMArena Multi-Turn | 1082 | 1296 |
| WildBench | — | 81.3% |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemini 1.5 Pro (May 2024)?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemini 1.5 Pro (May 2024) better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemini 1.5 Pro (May 2024) share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.