Model comparison
DeepSeek-V3.1-Terminus vs Gemini 1.0 Pro
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 27.3 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 1.0 Pro in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 9.3.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 45.9% for Gemini 1.0 Pro.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Gemini 1.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 27.3 |
| Released | 2025-09-22 | 2023-12-13 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 24 |
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: 42.0 (#113), Gemini 1.0 Pro: 32.2 (#275)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1426 | 1108 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 55.5% |
| MBPP+ | — | 61.4% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1109 |
| DTBench | 81.3% | 45.9% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 117.04 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Math | 1402 | 1132 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 11.2% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | — | 34% |
| LMArena Expert | — | 1059 |
| MMLU | — | 70% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1407 | 1138 |
| LMArena Russian | 1436 | 1186 |
| LMArena Chinese | — | 1124 |
| LMArena French | — | 1145 |
| LMArena German | — | 1125 |
| LMArena Japanese | — | 1023 |
| LMArena Spanish | — | 1119 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1404 | 1114 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1421 | 1132 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1419 | 1149 |
| LMArena Creative Writing | 1403 | 1131 |
| LMArena Multi-Turn | 1411 | 1139 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemini 1.0 Pro?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 27.3 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemini 1.0 Pro better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 32.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 1.0 Pro share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 1.0 Pro has 24.