# DeepSeek-V3.1-Terminus vs Gemini 3.8 Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.2× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-gemini-3-8-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 3.8 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 25.7.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 52.9% for Gemini 3.8 Flash.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 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 3.8 Flash |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.6 | 59.5 |
| Rank | 96 | 13 |
| Context | 164K | 1.05M |
| Input $/M | $0.30 | $0.75 |
| Output $/M | $1 | $3.75 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Gemini 3.8 Flash: 56.4 (#17)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| SciCode | 40.6% | 56.6% |
| LMArena Coding | 1426 | 1512 |
| ALE-Bench | 745.17 | 1,270 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1581 |
| FrontierSWE | — | 19.6% |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- Gemini 3.8 Flash: 40.3 (#22)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Gemini 3.8 Flash: 64.7 (#13)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| CritPt | 1.7% | 18.3% |
| LMArena Hard Prompts | 1427 | 1506 |
| DTBench | 81.3% | 95.7% |
| LMCA | 28.6% | 52.9% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 97.4% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 157.13 |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Gemini 3.8 Flash: 65.2 (#22)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Math | 1402 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Gemini 3.8 Flash: 74.9 (#2)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| LMArena Expert | — | 1529 |

## Multimodal

- DeepSeek-V3.1-Terminus: —
- Gemini 3.8 Flash: 40.9 (#33)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1312 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Gemini 3.8 Flash: 57.9 (#5)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1407 | 1486 |
| LMArena Russian | 1434 | 1507 |
| LMArena Chinese | — | 1547 |
| LMArena French | — | 1502 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1505 |
| LMArena Korean | — | 1479 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Gemini 3.8 Flash: 78.2 (#11)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1489 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Gemini 3.8 Flash: 46.2 (#23)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1426 | 1506 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Gemini 3.8 Flash: 72.1 (#16)

| Benchmark | DeepSeek-V3.1-Terminus | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1420 | 1494 |
| LMArena Creative Writing | 1404 | 1485 |
| LMArena Multi-Turn | 1411 | 1503 |
| EQ-Bench Creative Writing | — | 1748 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.2× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1-Terminus or Gemini 3.8 Flash?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is DeepSeek-V3.1-Terminus or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 164K.

### How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 3.8 Flash share?

15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 3.8 Flash has 46.