Gemma 4 31B (Reasoning) vs MiMo V2.6 Flash (Reasoning)
Results updated 14 November 2026 · Both in Terminus-2 · How we benchmark
Verdict
Not comparable yet: MiMo V2.6 Flash (Reasoning) is not yet ranked.
- Cost per task
- $0.018 vs No data
- Time per task
- 2.1 min vs No data
- Tokens per attempt
- 93k vs No data
- Image input
- Yes vs Yes
Not yet ranked. MiMo V2.6 Flash (Reasoning), Terminus-2: no Earth-Bench V2, GeoBenchX or GS-QA2 score yet. Not in the Agent Index, cost and time charts until it has a score on every index evaluation. Results so far are in the side-by-side table.
Charts for each: Gemma 4 31B (Reasoning), Terminus-2 · MiMo V2.6 Flash (Reasoning), Terminus-2.
Side by side
| Metric | Gemma 4 31B (Reasoning), Terminus-2 | MiMo V2.6 Flash (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 55 | No data |
| Geospatial Agent Index: Text + vision | No data | No data |
| Earth-Bench V2 score | 44 | No data |
| GeoBenchX score | 61 | No data |
| GS-QA2 score | 61 | No data |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 83 | No data |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 63 | No data |
| OGD4All score (standalone; in no index) | 85 | No data |
| GeoNatureAgent score (standalone; in no index) | 60 | No data |
| MultiGlobeQA score (standalone; in no index) | 30 | No data |
| GeoAgentEval score (standalone; in no index) | 88 | No data |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 59 | No data |
| Change detection score | 52 | No data |
| GIS analysis score | 56 | No data |
| Climate and time series score | 47 | No data |
| Making maps score | 70 | No data |
| Cost per task | $0.018 | No data |
| Time per task (at 100 output tokens/s) | 2.1 min | No data |
| Tokens per attempt | 93k | No data |
| Turns per attempt | 9.0 | No data |
| Input price per 1M tokens | $0.17 | $0.14 |
| Output price per 1M tokens | $0.40 | $0.28 |
| Context window | 262,144 | 1,048,576 |
| Image input | Yes | Yes |
| Developer | Xiaomi |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Gemma 4 31B (Reasoning), Terminus-2 or MiMo V2.6 Flash (Reasoning), Terminus-2?
Not comparable yet: MiMo V2.6 Flash (Reasoning), Terminus-2 is not yet ranked (no Earth-Bench V2, GeoBenchX or GS-QA2 score yet).
Which is cheaper per task, Gemma 4 31B (Reasoning), Terminus-2 or MiMo V2.6 Flash (Reasoning), Terminus-2?
Not known yet: MiMo V2.6 Flash (Reasoning), Terminus-2 has no cost data.
Which writes fewer output tokens per task, Gemma 4 31B (Reasoning), Terminus-2 or MiMo V2.6 Flash (Reasoning), Terminus-2?
Not known yet: MiMo V2.6 Flash (Reasoning), Terminus-2 has no output tokens data.
Which has the larger context window, Gemma 4 31B (Reasoning), Terminus-2 or MiMo V2.6 Flash (Reasoning), Terminus-2?
MiMo V2.6 Flash (Reasoning), Terminus-2, 1,048,576 tokens to 262,144 tokens.