Model comparison
DeepSeek-V3.1-Terminus vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.3× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeek
GoogleSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Gemini 3.6 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 26.4.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 44.9% for Gemini 3.6 Flash.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Gemini 3.6 Flash | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 54.1 |
| Released | 2025-09-22 | 2026-07-21 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 147K | 66K |
| Input $ / M tokens | $0.27 | $0.75 |
| Output $ / M tokens | $1 | $3.75 |
| Results tracked | 16 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Gemini 3.6 Flash: 50.0 (#48)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| SciCode | 40.6% | 52.7% |
| LMArena Coding | 1426 | 1491 |
| ALE-Bench | 745.17 | 715.52 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| LMArena WebDev | — | 1538 |
| WeirdML | — | 56.1% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 3.6 Flash: 32.3 (#65)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| GDP.pdf | — | 14% |
Reasoning Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Gemini 3.6 Flash: 58.8 (#22)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| CritPt | 1.7% | 10.6% |
| LMArena Hard Prompts | 1426 | 1485 |
| DTBench | 81.3% | 95.5% |
| LMCA | 28.6% | 44.9% |
| ARC-AGI-2 | — | 60.4% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 89% |
| ARC-AGI-1 | — | 91.2% |
| Chess Puzzles | — | 43% |
| Mystery Game Puzzles | — | 30% |
| Epoch Capabilities Index | — | 154.25 |
Math Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Gemini 3.6 Flash: 57.3 (#40)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Math | 1402 | 1505 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| OTIS Mock AIME 2024-2025 | — | 94.2% |
| ProofBench | — | 36% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 3.6 Flash: 67.8 (#8)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | — | 94.1% |
| SimpleQA Verified | — | 66.2% |
| LMArena Expert | — | 1488 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 3.6 Flash: 38.5 (#64)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | — | 1298 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
Multilingual Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Gemini 3.6 Flash: 56.5 (#19)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1407 | 1469 |
| LMArena Russian | 1436 | 1487 |
| LMArena Chinese | — | 1531 |
| LMArena French | — | 1504 |
| LMArena German | — | 1478 |
| LMArena Japanese | — | 1476 |
| LMArena Korean | — | 1431 |
| LMArena Spanish | — | 1475 |
Instruction Following Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Gemini 3.6 Flash: 77.0 (#33)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1404 | 1466 |
Long Context Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Gemini 3.6 Flash: 45.1 (#50)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1421 | 1474 |
Writing & Preference Gemini 3.6 Flash leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Gemini 3.6 Flash: 68.2 (#27)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1419 | 1479 |
| LMArena Creative Writing | 1403 | 1465 |
| LMArena Multi-Turn | 1411 | 1481 |
| EQ-Bench Creative Writing | — | 1604 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.3× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Gemini 3.6 Flash?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.
Is DeepSeek-V3.1-Terminus or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.6 Flash does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 3.6 Flash share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 3.6 Flash has 46.