Terminus-2 – Gemma 4 26B A4B (thinking on) vs. Codex – GPT-6 Luna (xhigh): geospatial agent comparison
Comparison between Terminus-2 – Gemma 4 26B A4B (thinking on) and Codex – GPT-6 Luna (xhigh) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.
Side by side
| Metric | Terminus-2 – Gemma 4 26B A4B (thinking on) | Codex – GPT-6 Luna (xhigh) |
|---|---|---|
| Geospatial Agent Index | 62 | 77* (partial: 1.9 of 3 attempts) |
| GeoAgentBench score | 87 | 99 |
| GeoBenchX score | 53 | 60 |
| Earth-Bench score | 34 | 55 |
| GeoAnalystBench score | 72 | 95 |
| Raster and remote sensing score | 57 | 75 |
| Vector and overlay score | 74 | 78 |
| Networks and routing score | 87 | 100 |
| Climate and time series score | 50 | 75 |
| Spatial statistics and interpolation score | 57 | 63 |
| Mapping and cartography score | 71 | 64 |
| Recognising infeasible requests score | 43 | 62 |
| Cost per task | $0.016 | $0.0092 |
| Time per task | 7.0 min | 3.4 min |
| Tokens per attempt | 127k | 236k |
| Turns per attempt | 9.9 | 9.8 |
| Attempts decided | 870 | 512 |
| Input price per 1M tokens | $0.10 | $0.10 |
| Output price per 1M tokens | $0.30 | $0.50 |
| Context window | 256,000 | No data |
| Image input | Yes | No data |
| Developer | OpenAI |
Charts
Geospatial Agent Index
Equal-weight average of the evaluation scores, 0 to 100 · Higher is better
First eight selected entries in metric order. Full results in table view.
Data table: Geospatial Agent Index
| Model | Creator | Geospatial Agent Index | Range while attempts are pending | Benchmarks covered | Coverage (attempts) |
|---|---|---|---|---|---|
| Codex – GPT-6 Luna (xhigh) | OpenAI | 77* (partial: 1.9 of 3 attempts) | 72 to 78 | 4 of 4 | 512 of 870 planned attempts |
| Terminus-2 – Gemma 4 26B A4B (thinking on) | 62 | No pending judgements | 4 of 4 | 870 of 870 planned attempts |
Codex – GPT-6 Luna (xhigh)
Terminus-2 – Gemma 4 26B A4B (thinking on)Cost per task
Average cost per task (USD) · Lower is better
First eight selected entries in metric order. Full results in table view.
Data table: Cost per task
| Model | Creator | Cost per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – Gemma 4 26B A4B (thinking on) | $0.016 | 870 of 870 planned attempts | |
| Codex – GPT-6 Luna (xhigh) | OpenAI | $0.0092 | 560 of 870 planned attempts |
Time per task
Average agent wall time per task · Lower is better
First eight selected entries in metric order. Full results in table view.
Data table: Time per task
| Model | Creator | Time per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – Gemma 4 26B A4B (thinking on) | 7.0 min | 870 of 870 planned attempts | |
| Codex – GPT-6 Luna (xhigh) | OpenAI | 3.4 min | 560 of 870 planned attempts |
Frequently asked questions
- Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Luna (xhigh)?
- Codex – GPT-6 Luna (xhigh), at 77 against 62 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – Gemma 4 26B A4B (thinking on): 870 of 870 planned attempts. Codex – GPT-6 Luna (xhigh): 512 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
- Which is cheaper per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Luna (xhigh)?
- Codex – GPT-6 Luna (xhigh), at $0.0092 against $0.016 for Terminus-2 – Gemma 4 26B A4B (thinking on).
- Which is faster per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Luna (xhigh)?
- Codex – GPT-6 Luna (xhigh), at 3.4 min against 7.0 min for Terminus-2 – Gemma 4 26B A4B (thinking on).
- Which has the larger context window, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Luna (xhigh)?
- Not known yet: Codex – GPT-6 Luna (xhigh) has no context window data.
More: Terminus-2 – Gemma 4 26B A4B (thinking on) · Codex – GPT-6 Luna (xhigh) · all comparisons