Llama 3.3 70B (Non-reasoning), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2
Llama 3.3 70B (Non-reasoning), Terminus-2 against Step 5 Preview (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | Llama 3.3 70B (Non-reasoning), Terminus-2 | Step 5 Preview (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 8 | 34 |
| Geospatial Agent Index: Text + vision | No image input | No data |
| Earth-Bench V2 score | 9 | 32 |
| GeoBenchX score | 6 | 17 |
| GS-QA2 score | 10 | 52 |
| Vision agents score | No image input | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 8 | 50 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 0 | 53 |
| 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 | 7 | 35 |
| GIS analysis score | 12 | 67 |
| Climate and time series score | 10 | 34 |
| Spatial statistics score | 0 | 0 |
| Making maps score | 2 | 19 |
| Recognising infeasible requests score | 13 | 24 |
| Cost per task | $0.023 | $0.071 |
| Time per task (at 100 output tokens/s) | 2.1 min | 7.9 min (estimated) |
| Tokens per attempt | 62k | 90k |
| Turns per attempt | 14.4 | 11.1 |
| Input price per 1M tokens | $0.29 | $1.00 |
| Output price per 1M tokens | $2.25 | $2.70 |
| Context window | 24,000 | 1,024,000 |
| Image input | No | Yes |
| Developer | Meta | StepFun |
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 |
|---|---|---|
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | 34 |
| Llama 3.3 70B (Non-reasoning), Terminus-2 | Meta | 8 |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Developer | Cost per task |
|---|---|---|
| Llama 3.3 70B (Non-reasoning), Terminus-2 | Meta | $0.023 |
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | $0.071 |
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 |
|---|---|---|
| Llama 3.3 70B (Non-reasoning), Terminus-2 | Meta | 2k |
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | 10k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Llama 3.3 70B (Non-reasoning), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, 34 to 8.
Which is cheaper per task, Llama 3.3 70B (Non-reasoning), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Llama 3.3 70B (Non-reasoning), Terminus-2, $0.023 to $0.071.
Which writes fewer output tokens per task, Llama 3.3 70B (Non-reasoning), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Llama 3.3 70B (Non-reasoning), Terminus-2, 2k to 10k.
Which has the larger context window, Llama 3.3 70B (Non-reasoning), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, 1,024,000 tokens to 24,000 tokens.
More: Llama 3.3 70B (Non-reasoning), Terminus-2 · Step 5 Preview (Reasoning), Terminus-2 · All comparisons