MiniMax M3 (Reasoning) vs Nemotron 3.5 Super 120B (Reasoning)
Results updated 13 November 2026 · Both in Terminus-2 · How we benchmark
Verdict
Not comparable yet: MiniMax M3 (Reasoning) is not yet ranked.
- Cost per task
- No data vs $0.014
- Time per task
- No data vs 13.8 min
- Tokens per attempt
- No data vs 105k
- Image input
- Yes vs No
Not yet ranked. MiniMax M3 (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: MiniMax M3 (Reasoning), Terminus-2 · Nemotron 3.5 Super 120B (Reasoning), Terminus-2.
Side by side
| Metric | MiniMax M3 (Reasoning), Terminus-2 | Nemotron 3.5 Super 120B (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | No data | 56 |
| Geospatial Agent Index: Text + vision | No data | No data |
| Earth-Bench V2 score | No data | 49 |
| GeoBenchX score | No data | 56 |
| GS-QA2 score | No data | 63 |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | No data | 83 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | No data | 79 |
| OGD4All score (standalone; in no index) | No data | 85 |
| GeoNatureAgent score (standalone; in no index) | No data | 96 |
| MultiGlobeQA score (standalone; in no index) | No data | 70 |
| GeoAgentEval score (standalone; in no index) | No data | 84 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | No data | 54 |
| Change detection score | No data | 56 |
| GIS analysis score | No data | 70 |
| Climate and time series score | No data | 50 |
| Making maps score | No data | 70 |
| Cost per task | No data | $0.014 |
| Time per task (at 100 output tokens/s) | No data | 13.8 min |
| Tokens per attempt | No data | 105k |
| Turns per attempt | No data | 10.5 |
| Input price per 1M tokens | $0.30 | $0.20 |
| Output price per 1M tokens | $1.20 | $0.50 |
| Context window | 1,048,576 | 262,144 |
| Image input | Yes | No |
| Developer | MiniMax | NVIDIA |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, MiniMax M3 (Reasoning), Terminus-2 or Nemotron 3.5 Super 120B (Reasoning), Terminus-2?
Not comparable yet: MiniMax M3 (Reasoning), Terminus-2 is not yet ranked (no Earth-Bench V2, GeoBenchX or GS-QA2 score yet).
Which is cheaper per task, MiniMax M3 (Reasoning), Terminus-2 or Nemotron 3.5 Super 120B (Reasoning), Terminus-2?
Not known yet: MiniMax M3 (Reasoning), Terminus-2 has no cost data.
Which writes fewer output tokens per task, MiniMax M3 (Reasoning), Terminus-2 or Nemotron 3.5 Super 120B (Reasoning), Terminus-2?
Not known yet: MiniMax M3 (Reasoning), Terminus-2 has no output tokens data.
Which has the larger context window, MiniMax M3 (Reasoning), Terminus-2 or Nemotron 3.5 Super 120B (Reasoning), Terminus-2?
MiniMax M3 (Reasoning), Terminus-2, 1,048,576 tokens to 262,144 tokens.