Model comparison
DeepSeek LLM 67B vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 24.8 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 Flash Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Flash Preview leads 58.8 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 95.6% for Gemini 3 Flash Preview.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.8 | 52.3 |
| Released | 2023-11-29 | 2025-12-17 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 15 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 31.3 (#273), Gemini 3 Flash Preview: 51.5 (#35)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Coding | 1096 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |
| ALE-Bench | — | 1,367 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemini 3 Flash Preview: 38.6 (#27)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 15.9 (#300), Gemini 3 Flash Preview: 49.2 (#35)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1070 | 1465 |
| Epoch Capabilities Index | 110.54 | 151.83 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 89.1% |
| LMCA | — | 43.1% |
| ForecastBench | — | 58.5 |
Math Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 8.1 (#318), Gemini 3 Flash Preview: 51.4 (#42)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 95.6% |
| LMArena Math | 1108 | 1472 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 15% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 7.1 (#308), Gemini 3 Flash Preview: 58.8 (#30)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 24.6% | 89.4% |
| SimpleQA Verified | — | 66.8% |
| Vectara Hallucination Rate | — | 13.5% |
| LMArena Expert | — | 1461 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemini 3 Flash Preview: 45.3 (#15)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
Multilingual Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 29.5 (#262), Gemini 3 Flash Preview: 55.9 (#26)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1073 | 1458 |
| LMArena Chinese | 1132 | 1510 |
| LMArena French | — | 1478 |
| LMArena German | — | 1497 |
| LMArena Japanese | — | 1488 |
| LMArena Korean | — | 1443 |
| LMArena Russian | — | 1480 |
| LMArena Spanish | — | 1470 |
Instruction Following Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 55.7 (#272), Gemini 3 Flash Preview: 75.8 (#52)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1079 | 1437 |
Long Context Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 33.1 (#260), Gemini 3 Flash Preview: 44.4 (#63)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1092 | 1452 |
Writing & Preference Gemini 3 Flash Preview leads
DeepSeek LLM 67B: 31.8 (#277), Gemini 3 Flash Preview: 65.6 (#44)
| Benchmark | DeepSeek LLM 67B | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1105 | 1466 |
| LMArena Creative Writing | 1067 | 1457 |
| LMArena Multi-Turn | 1082 | 1471 |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemini 3 Flash Preview share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 3 Flash Preview has 59.