Terminus-2 – Llama 3.3 70B (Non-reasoning) vs. Codex – GPT-5.6 Luna (xhigh): geospatial agent comparison
Comparison between Terminus-2 – Llama 3.3 70B (Non-reasoning) and Codex – GPT-5.6 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 – Llama 3.3 70B (Non-reasoning) | Codex – GPT-5.6 Luna (xhigh) |
|---|---|---|
| Geospatial Agent Index | 8* | 77* (partial: attempt 1 on 210 of 488 tasks) |
| Earth-Bench V2 score | 9 | 86 |
| GeoBenchX score | 6 | 60 |
| GS-QA2 score | 10 | 85 |
| GeoAgentBench score (guided GIS workflow; outside the index) | 8 | 98 |
| GeoAnalystBench score (guided GIS workflow; outside the index) | 0 | 100 |
| Raster and remote sensing score | 7 | 82 |
| Vector and overlay score | 12 | 86 |
| Climate and time series score | 10 | 90 |
| Spatial statistics and interpolation score | 0 | 33 |
| Mapping and cartography score | 2 | 75 |
| Recognising infeasible requests score | 13 | 50 |
| Cost per task | $0.023 | $0.012 |
| Time per task | 3.1 min | 2.5 min |
| Tokens per attempt | 62k | 176k |
| Turns per attempt | 14.4 | 9.7 |
| Attempts decided | 488 | 210 |
| Input price per 1M tokens | $0.29 | $0.20 |
| Output price per 1M tokens | $2.25 | $1.20 |
| Context window | 24,000 | No data |
| Image input | No | No data |
| Developer | Meta | OpenAI |
Charts
Partial coverage. Codex – GPT-5.6 Luna (xhigh): 49 of 117 Earth-Bench V2 tasks; 20 of 150 GeoBenchX tasks; 141 of 221 GS-QA2 tasks. Grey placeholders identify these entries in the index, cost and output token charts; their height does not represent a value. Comparable bars appear when first-attempt coverage is complete. Their available results remain in the side-by-side table.
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) |
|---|---|---|---|---|---|
| Terminus-2 – Llama 3.3 70B (Non-reasoning) | Meta | 8* | No pending judgements; coverage incomplete; 23 results awaiting review | 3 of 3 | 488 of 722 scheduled attempts |
Cost per task
Average cost per task (USD) · Lower is better
First eight selected entries in metric order. Full results in table view.
How to read this chart
Not shown: partial coverage. 1 entries without a first attempt on every index task. What is still running is on the models page.
Data table: Cost per task
| Model | Creator | Cost per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – Llama 3.3 70B (Non-reasoning) | Meta | $0.023 | 488 of 722 scheduled attempts |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
First eight selected entries in metric order. Full results in table view.
How to read this chart
Not shown: partial coverage. 1 entries without a first attempt on every index task. What is still running is on the models page.
Data table: Output tokens per task
| Model | Creator | Output tokens per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – Llama 3.3 70B (Non-reasoning) | Meta | 2k | 488 of 722 scheduled attempts |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Codex – GPT-5.6 Luna (xhigh)?
Which is cheaper per task, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Codex – GPT-5.6 Luna (xhigh)?
Which writes fewer output tokens per task, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Codex – GPT-5.6 Luna (xhigh)?
Which has the larger context window, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Codex – GPT-5.6 Luna (xhigh)?
More: Terminus-2 – Llama 3.3 70B (Non-reasoning) · Codex – GPT-5.6 Luna (xhigh) · all comparisons