Model comparison
DeepSeek-V3.1-Terminus vs Gemini 1.5 Pro (May 2024)
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 31.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
GoogleSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemini 1.5 Pro (May 2024) in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 12.3.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 59% for Gemini 1.5 Pro (May 2024).
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 31.9 |
| Released | 2025-09-22 | 2024-02-15 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 45 |
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 1.5 Pro (May 2024): 33.8 (#239)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Coding | 1426 | 1294 |
| SciCode | 40.6% | — |
| WeirdML | — | 22.2% |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 1.5 Pro (May 2024): 17.8 (#137)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemini 1.5 Pro (May 2024): 12.3 (#332)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1296 |
| DTBench | 81.3% | 59% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 27.1% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 89.2% |
| Epoch Capabilities Index | — | 131.73 |
| ForecastBench | — | 58.4 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemini 1.5 Pro (May 2024): 24.4 (#260)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Math | 1402 | 1315 |
| OTIS Mock AIME 2024-2025 | — | 23.1% |
| Omni-MATH | — | 36.4% |
| MATH Level 5 | — | 70.4% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 1.5 Pro (May 2024): 29.3 (#228)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | — | 57.2% |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| GPQA (HELM) | — | 53.4% |
| LMArena Expert | — | 1279 |
| MMLU | — | 86.9% |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 1.5 Pro (May 2024): 36.2 (#72)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemini 1.5 Pro (May 2024): 45.5 (#169)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1407 | 1312 |
| LMArena Russian | 1434 | 1320 |
| LMArena Chinese | — | 1331 |
| LMArena French | — | 1301 |
| LMArena German | — | 1286 |
| LMArena Japanese | — | 1292 |
| LMArena Korean | — | 1298 |
| LMArena Spanish | — | 1310 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemini 1.5 Pro (May 2024): 68.8 (#180)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1406 | 1297 |
| IFEval | — | 83.7% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemini 1.5 Pro (May 2024): 39.7 (#164)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1426 | 1308 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemini 1.5 Pro (May 2024): 52.5 (#167)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1420 | 1319 |
| LMArena Creative Writing | 1404 | 1333 |
| LMArena Multi-Turn | 1411 | 1296 |
| WildBench | — | 81.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemini 1.5 Pro (May 2024)?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 31.9 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemini 1.5 Pro (May 2024) better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 33.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 1.5 Pro (May 2024) share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.