Model comparison
DeepSeek LLM 67B vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 24.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
GoogleSummary
- They share 12 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemini 2.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 39.9 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 73.1% for Gemini 2.5 Flash.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Gemini 2.5 Flash | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 39.3 |
| Released | 2023-11-29 | 2025-04-17 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 15 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
DeepSeek LLM 67B: 31.9 (#278), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1096 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| ALE-Bench | — | 661.88 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Gemini 2.5 Flash leads
DeepSeek LLM 67B: 16.5 (#304), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1422 |
| Epoch Capabilities Index | 110.5 | 143.03 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 2.7% |
| DTBench | — | 76.5% |
| LMCA | — | 27.5% |
| ForecastBench | — | 60.6 |
Math Gemini 2.5 Flash leads
DeepSeek LLM 67B: 8.7 (#324), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 73.1% |
| LMArena Math | 1108 | 1415 |
| Omni-MATH | — | 38.5% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Flash leads
DeepSeek LLM 67B: 7.0 (#313), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |
| LMArena Expert | — | 1426 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
DeepSeek LLM 67B: 29.4 (#267), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1073 | 1409 |
| LMArena Chinese | 1132 | 1450 |
| LMArena French | — | 1433 |
| LMArena German | — | 1418 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1385 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1421 |
Instruction Following Gemini 2.5 Flash leads
DeepSeek LLM 67B: 55.4 (#277), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1079 | 1405 |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
DeepSeek LLM 67B: 33.1 (#265), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1092 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
DeepSeek LLM 67B: 31.6 (#282), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1105 | 1417 |
| LMArena Creative Writing | 1067 | 1400 |
| LMArena Multi-Turn | 1082 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| WildBench | — | 81.7% |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemini 2.5 Flash share?
12 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 2.5 Flash has 54.