gpt-oss-120b (low), Terminus-2 vs. Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2
gpt-oss-120b (low), Terminus-2 against Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | gpt-oss-120b (low), Terminus-2 | Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 31 | 11 |
| Geospatial Agent Index: Text + vision | No image input | No data |
| Earth-Bench V2 score | 28 | 16 |
| GeoBenchX score | 37 | 12 |
| GS-QA2 score | 29 | 4 |
| Vision agents score | No image input | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 60 | 10 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 47 | 32 |
| OGD4All score (standalone; in no index) | No data | No data |
| GeoNatureAgent score (standalone; in no index) | No data | No data |
| MultiGlobeQA score (standalone; in no index) | No data | No data |
| GeoAgentEval score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 25 | 11 |
| GIS analysis score | 34 | 7 |
| Climate and time series score | 29 | 15 |
| Spatial statistics score | 8 | 0 |
| Making maps score | 21 | 7 |
| Recognising infeasible requests score | 60 | 12 |
| Cost per task | $0.0046 | $0.012 |
| Time per task (at 100 output tokens/s) | 0.5 min | 4.9 min |
| Tokens per attempt | 11k | 249k |
| Turns per attempt | 2.9 | 17.3 |
| Input price per 1M tokens | $0.35 | $0.070 |
| Output price per 1M tokens | $0.75 | $0.20 |
| Context window | 128,000 | 262,144 |
| Image input | No | No |
| Developer | OpenAI | NVIDIA |
Charts
Geospatial Agent Index
Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index |
|---|---|---|
| gpt-oss-120b (low), Terminus-2 | OpenAI | 31 |
| Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 | NVIDIA | 11 |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Developer | Cost per task |
|---|---|---|
| gpt-oss-120b (low), Terminus-2 | OpenAI | $0.0046 |
| Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 | NVIDIA | $0.012 |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
Data table: Output tokens per task
| Model | Developer | Output tokens per task |
|---|---|---|
| gpt-oss-120b (low), Terminus-2 | OpenAI | 2k |
| Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 | NVIDIA | 6k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, gpt-oss-120b (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
gpt-oss-120b (low), Terminus-2, 31 to 11.
Which is cheaper per task, gpt-oss-120b (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
gpt-oss-120b (low), Terminus-2, $0.0046 to $0.012.
Which writes fewer output tokens per task, gpt-oss-120b (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
gpt-oss-120b (low), Terminus-2, 2k to 6k.
Which has the larger context window, gpt-oss-120b (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2, 262,144 tokens to 128,000 tokens.
More: gpt-oss-120b (low), Terminus-2 · Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 · All comparisons