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

> DeepSeek-V3.1-Terminus and Step 3.5 Flash score almost the same on the Noometry Index (42.6 vs 41.7), so choose on price, context window or the category you care about most.

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

## Summary

- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 5 categories and Step 3.5 Flash in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 40.6 to 35.7.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- Step 3.5 Flash accepts more context: 256K tokens versus 164K.

## Snapshot

| | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 42.6 | 41.7 |
| Rank | 96 | 116 |
| Context | 164K | 256K |
| Input $/M | $0.30 | $0.10 |
| Output $/M | $1 | $0.30 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1426 | 1436 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1411 |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1402 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1422 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1407 | 1386 |
| LMArena Russian | 1434 | 1385 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1385 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1426 | 1402 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | DeepSeek-V3.1-Terminus | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1420 | 1403 |
| LMArena Creative Writing | 1404 | 1357 |
| LMArena Multi-Turn | 1411 | 1405 |

## FAQ

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

DeepSeek-V3.1-Terminus and Step 3.5 Flash score almost the same on the Noometry Index (42.6 vs 41.7), so choose on price, context window or the category you care about most.

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

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.

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

They score almost the same on coding (41.5 vs 41.7); test both on your own repository before choosing.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 164K.

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

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Step 3.5 Flash has 19.