gpt-oss-120b (high) vs Nemotron 3.5 Bolt E4B (Reasoning)
Results updated 9 November 2026 · Both in Terminus-2 · How we benchmark
Verdict
gpt-oss-120b (high) clearly beats Nemotron 3.5 Bolt E4B (Reasoning) by 42 points, and is faster.
- Cost per task
- $0.026 vs No data
- Time per task
- 3.0 min vs 5.2 min
- Tokens per attempt
- 57k vs 341k
- Image input
- No vs No
gpt-oss-120b (high), Terminus-2 scores higher than Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2 on all 3 evaluations scored for both.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | gpt-oss-120b (high) | Nemotron 3.5 Bolt E4B (Reasoning) |
|---|---|---|
| Change detection | 60 | 8 |
| Climate and time series | 54 | 6 |
| Remote sensing and raster analysis | 41 | 1 |
| Making maps | 40 | 2 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: gpt-oss-120b (high), Terminus-2 · Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2.
Side by side
| Metric | gpt-oss-120b (high), Terminus-2 | Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 46 | 4 |
| Geospatial Agent Index: Text + vision | No image input | No data |
| Earth-Bench V2 score | 50 | 5 |
| GeoBenchX score | 45 | 3 |
| GS-QA2 score | 42 | 3 |
| Vision agents score | No image input | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 70 | 4 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 53 | 5 |
| OGD4All score (standalone; in no index) | No data | 21 |
| GeoNatureAgent score (standalone; in no index) | No data | 0 |
| MultiGlobeQA score (standalone; in no index) | No data | 16 |
| GeoAgentEval score (standalone; in no index) | No data | 40 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 41 | 1 |
| Change detection score | 60 | 8 |
| GIS analysis score | 41 | 3 |
| Climate and time series score | 54 | 6 |
| Making maps score | 40 | 2 |
| Cost per task | $0.026 | No data |
| Time per task (at 100 output tokens/s) | 3.0 min | 5.2 min |
| Tokens per attempt | 57k | 341k |
| Turns per attempt | 5.8 | 24.4 |
| Input price per 1M tokens | $0.15 | No data |
| Output price per 1M tokens | $0.59 | No data |
| Context window | 128,000 | 65,536 |
| Image input | No | No |
| Developer | OpenAI | NVIDIA |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, gpt-oss-120b (high), Terminus-2 or Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2?
gpt-oss-120b (high), Terminus-2, 46 to 4.
Which is cheaper per task, gpt-oss-120b (high), Terminus-2 or Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2?
Not known yet: Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2 has no cost data.
Which writes fewer output tokens per task, gpt-oss-120b (high), Terminus-2 or Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2?
Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2, 14k to 15k.
Which has the larger context window, gpt-oss-120b (high), Terminus-2 or Nemotron 3.5 Bolt E4B (Reasoning), Terminus-2?
gpt-oss-120b (high), Terminus-2, 128,000 tokens to 65,536 tokens.