Model comparison
DeepSeek LLM 67B vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 24.8 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
GoogleSummary
- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemini 2.5 Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 95.9% for Gemini 2.5 Pro.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Gemini 2.5 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.8 | 44.9 |
| Released | 2023-11-29 | 2025-03-25 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 15 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
DeepSeek LLM 67B: 31.3 (#273), Gemini 2.5 Pro: 42.8 (#86)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Coding | 1096 | 1452 |
| SWE-bench Verified | — | 57.6% |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| LMArena WebDev | — | 1227 |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| WeirdML | — | 54% |
| LiveBench Coding | — | 85.9% |
| CadEval | — | 64% |
| ALE-Bench | — | 785.52 |
| AlgoTune | — | 1.51 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemini 2.5 Pro: 29.1 (#81)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | — | 32.6% |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| τ²-bench Banking | — | 13.7% |
| DeepResearch Bench | — | 42.8% |
| BALROG | — | 43.3% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 55.4% |
| Vending-Bench 2 | — | 573.64 |
Reasoning Gemini 2.5 Pro leads
DeepSeek LLM 67B: 15.9 (#300), Gemini 2.5 Pro: 28.8 (#85)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1070 | 1455 |
| Epoch Capabilities Index | 110.54 | 145.32 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 62.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 41% |
| CritPt | — | 2% |
| EnigmaEval | — | 5.6% |
| LiveBench Reasoning | — | 89.8% |
| DTBench | — | 82.4% |
| LiveBench Data Analysis | — | 79.9% |
| LMCA | — | 34.8% |
| ForecastBench | — | 61.3 |
| LiveBench | — | 82.3% |
Math Gemini 2.5 Pro leads
DeepSeek LLM 67B: 8.1 (#318), Gemini 2.5 Pro: 31.9 (#191)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 84.7% |
| LMArena Math | 1108 | 1450 |
| MATH Level 5 | 6.4% | 95.9% |
| FrontierMath (Tiers 1-3) | — | 24.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | — | 41.6% |
| LiveBench Math | — | 90.2% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Pro leads
DeepSeek LLM 67B: 7.1 (#308), Gemini 2.5 Pro: 55.8 (#41)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| GPQA Diamond | 24.6% | 85.3% |
| Humanity's Last Exam | — | 21.6% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.6% |
| Vectara Hallucination Rate | — | 7% |
| GPQA (HELM) | — | 74.9% |
| LMArena Expert | — | 1452 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemini 2.5 Pro: 44.5 (#16)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | — | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
DeepSeek LLM 67B: 29.5 (#262), Gemini 2.5 Pro: 55.5 (#30)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1073 | 1452 |
| LMArena Chinese | 1132 | 1507 |
| LMArena French | — | 1473 |
| LMArena German | — | 1487 |
| LMArena Japanese | — | 1462 |
| LMArena Korean | — | 1435 |
| LMArena Russian | — | 1460 |
| LMArena Spanish | — | 1473 |
Instruction Following Gemini 2.5 Pro leads
DeepSeek LLM 67B: 55.7 (#272), Gemini 2.5 Pro: 75.2 (#71)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1079 | 1436 |
| LiveBench Instruction Following | — | 80.6% |
| IFEval | — | 84% |
Long Context Gemini 2.5 Pro leads
DeepSeek LLM 67B: 33.1 (#260), Gemini 2.5 Pro: 59.7 (#5)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1092 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
DeepSeek LLM 67B: 31.8 (#277), Gemini 2.5 Pro: 63.9 (#60)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1105 | 1458 |
| LMArena Creative Writing | 1067 | 1453 |
| LMArena Multi-Turn | 1082 | 1453 |
| Short-Story Creative Writing | — | 83.8% |
| EQ-Bench Creative Writing | — | 1421 |
| WildBench | — | 85.7% |
| LiveBench Language | — | 67.8% |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Gemini 2.5 Pro better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemini 2.5 Pro share?
15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 2.5 Pro has 78.