Model comparison
DeepSeek-V3.1-Terminus vs Gemini 2.0 Flash (Feb 2025)
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 34.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
GoogleSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 5 categories and Gemini 2.0 Flash (Feb 2025) in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 41.5 to 28.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 37.8% for Gemini 2.0 Flash (Feb 2025).
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 34.8 |
| Released | 2025-09-22 | 2024-12-06 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Gemini 2.0 Flash (Feb 2025): 28.2 (#308)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Coding | 1426 | 1351 |
| SWE-bench Verified (bash only) | — | 13.5% |
| Aider Polyglot | — | 38.2% |
| SciCode | 40.6% | — |
| WeirdML | — | 25.8% |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.0 Flash (Feb 2025): 28.0 (#85)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | — | 11.4% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemini 2.0 Flash (Feb 2025): 15.2 (#308)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 37.8% |
| LMArena Hard Prompts | 1427 | 1346 |
| DTBench | 81.3% | 63.2% |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31.1% |
| CritPt | 1.7% | — |
| EnigmaEval | — | 1.1% |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 135.36 |
| LiveBench | — | 66.9% |
Math Too close to call
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemini 2.0 Flash (Feb 2025): 36.1 (#127)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Math | 1402 | 1351 |
| OTIS Mock AIME 2024-2025 | — | 57.8% |
| Omni-MATH | — | 45.9% |
| LiveBench Math | — | 75.8% |
| MATH Level 5 | — | 82.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.0 Flash (Feb 2025): 32.0 (#207)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | — | 64.1% |
| Humanity's Last Exam | — | 6.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 55.6% |
| LMArena Expert | — | 1340 |
| MMLU | — | 79.7% |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.0 Flash (Feb 2025): 35.9 (#74)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemini 2.0 Flash (Feb 2025): 47.6 (#144)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1407 | 1342 |
| LMArena Russian | 1434 | 1351 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1390 |
| LMArena German | — | 1354 |
| LMArena Japanese | — | 1293 |
| LMArena Korean | — | 1314 |
| LMArena Spanish | — | 1363 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemini 2.0 Flash (Feb 2025): 74.6 (#91)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Instruction Following | 1406 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
| IFEval | — | 84.1% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemini 2.0 Flash (Feb 2025): 38.1 (#198)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Longer Query | 1426 | 1345 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemini 2.0 Flash (Feb 2025): 49.8 (#184)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1420 | 1354 |
| LMArena Creative Writing | 1404 | 1340 |
| LMArena Multi-Turn | 1411 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| EQ-Bench Creative Writing | — | 1128 |
| WildBench | — | 80% |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemini 2.0 Flash (Feb 2025)?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 34.8 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemini 2.0 Flash (Feb 2025) better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 2.0 Flash (Feb 2025) share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.