# DeepSeek-V3.1-Terminus vs Gemini 3.5 Flash

> Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 7.1× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-gemini-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Gemini 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.7 to 25.7.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 47.1% for Gemini 3.5 Flash.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.6 | 54.1 |
| Rank | 96 | 29 |
| Context | 164K | 1.05M |
| Input $/M | $0.30 | $1.50 |
| Output $/M | $1 | $9 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Gemini 3.5 Flash: 49.1 (#46)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| SciCode | 40.6% | 53.1% |
| LMArena Coding | 1426 | 1492 |
| ALE-Bench | 745.17 | 911.02 |
| SWE-bench Verified | — | 79.3% |
| DeepSWE | — | 37.4% |
| LMArena WebDev | — | 1499 |
| WeirdML | — | 62.6% |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- Gemini 3.5 Flash: 24.8 (#107)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| APEX-Agents | — | 27.5% |
| GBAEval | — | 6.7% |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | — | 5,396 |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Gemini 3.5 Flash: 62.7 (#16)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| CritPt | 1.7% | 13.1% |
| LMArena Hard Prompts | 1427 | 1488 |
| DTBench | 81.3% | 94.7% |
| LMCA | 28.6% | 47.1% |
| ARC-AGI-2 | — | 72.1% |
| SimpleBench | — | 76.7% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 92.6% |
| ARC-AGI-1 | — | 92.5% |
| Chess Puzzles | — | 50% |
| EnigmaEval | — | 25.4% |
| EBR-Bench | — | 4.8% |
| Mystery Game Puzzles | — | 32% |
| Surface Evolver Bench | — | 58.1% |
| Epoch Capabilities Index | — | 154.55 |
| ForecastBench | — | 59 |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Gemini 3.5 Flash: 60.5 (#30)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Math | 1402 | 1502 |
| FrontierMath (Tiers 1-3) | — | 62.8% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.3% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 31% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Gemini 3.5 Flash: 66.3 (#10)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| GPQA Diamond | — | 92.8% |
| SimpleQA Verified | — | 66.2% |
| LMArena Expert | — | 1493 |

## Multimodal

- DeepSeek-V3.1-Terminus: —
- Gemini 3.5 Flash: 45.7 (#13)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Vision | — | 1311 |
| Blueprint-Bench 2 | — | 33.6% |
| LMArena Document | — | 1463 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Gemini 3.5 Flash: 57.1 (#12)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1407 | 1475 |
| LMArena Russian | 1434 | 1491 |
| LMArena Chinese | — | 1525 |
| LMArena French | — | 1490 |
| LMArena German | — | 1500 |
| LMArena Japanese | — | 1481 |
| LMArena Korean | — | 1453 |
| LMArena Spanish | — | 1478 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Gemini 3.5 Flash: 77.2 (#29)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1466 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Gemini 3.5 Flash: 45.3 (#39)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1426 | 1481 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Gemini 3.5 Flash: 65.5 (#46)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.5 Flash |
|---|---|---|
| LMArena Text | 1420 | 1481 |
| LMArena Creative Writing | 1404 | 1467 |
| LMArena Multi-Turn | 1411 | 1482 |
| EQ-Bench 4 | — | 1087 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Gemini 3.5 Flash?

Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 7.1× less per token, which makes it the better buy when Gemini 3.5 Flash's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1-Terminus or Gemini 3.5 Flash?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Gemini 3.5 Flash lists at $1.50 and $9.

### Is DeepSeek-V3.1-Terminus or Gemini 3.5 Flash better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.1 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 164K.

### How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 3.5 Flash share?

15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 3.5 Flash has 54.