Model comparison
DeepSeek LLM 67B vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 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 0 categories and Gemini 3.1 Pro Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.1 Pro Preview leads 71.8 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 95.6% for Gemini 3.1 Pro Preview.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 56.7 |
| Released | 2023-11-29 | 2026-02-19 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 15 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 31.9 (#278), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Coding | 1096 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| MirrorCode | — | 8.9% |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 16.5 (#304), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| Chess Puzzles | 0% | 55% |
| LMArena Hard Prompts | 1070 | 1485 |
| Epoch Capabilities Index | 110.5 | 154.77 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.1% |
| LMCA | — | 53.8% |
| ForecastBench | — | 59 |
Math Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 8.7 (#324), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 95.6% |
| LMArena Math | 1108 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| ProofBench | — | 26% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 7.0 (#313), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 24.6% | 94.4% |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
| LMArena Expert | — | 1485 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 29.4 (#267), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1073 | 1477 |
| LMArena Chinese | 1132 | 1529 |
| LMArena French | — | 1487 |
| LMArena German | — | 1491 |
| LMArena Japanese | — | 1493 |
| LMArena Korean | — | 1455 |
| LMArena Russian | — | 1498 |
| LMArena Spanish | — | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 55.4 (#277), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1079 | 1466 |
Long Context Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 33.1 (#265), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1092 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
DeepSeek LLM 67B: 31.6 (#282), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | DeepSeek LLM 67B | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1105 | 1481 |
| LMArena Creative Writing | 1067 | 1482 |
| LMArena Multi-Turn | 1082 | 1488 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemini 3.1 Pro Preview share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 3.1 Pro Preview has 71.