Earth science knowledge
What a model knows about geospatial (GIS and Earth observation) work, with no tools and no internet.
Ongoing evaluation: results update as runs complete. Last updated 14 October 2026.
Score
Earth science knowledge score
Share of questions answered correctly, 0 to 100 · Higher is better
How to read this chart
Rows. Each model once, at its highest reasoning level with a quiz that counts; every level is in the table below the chart.
Data table: Earth science knowledge score
| Model | Score |
|---|---|
| Claude Opus 5.5 (xhigh) | 94.3 |
| Claude Sonnet 5.5 (xhigh) | 94.1 |
| Claude Opus 4.8 (high) | 93.3 |
| Claude Opus 5 (high) | 93.1 |
| Claude Opus 4.7 (high) | 92.8 |
| GPT-6.1 Sol (xhigh) | 92.5 |
| Kimi K2.7 Code (always on) | 92.1 |
| Kimi K3 (always on) | 92.0 |
| DeepSeek V4 Pro (max) | 91.9 |
| Claude Haiku 5.5 (xhigh) | 91.8 |
| GLM-5.3 (max, default) | 91.8 |
| Kimi K2.6 (always on) | 91.8 |
| GLM-5.3-Flash (max) | 91.8 |
| DeepSeek V4 Flash (max) | 91.5 |
| Claude Sonnet 5 (high) | 91.4 |
| GPT-6 Luna (xhigh) | 91.3 |
| Qwen 3.8 27B (xhigh) | 91.1 |
| gpt-oss-120b (high) | 89.8 |
| Claude Haiku 4.5 (thinking 32k) | 89.0 |
| GLM-5.2 (max) | 89.0 |
| Gemma 4 26B A4B (thinking on) | 88.7 |
| GLM-4.7-Flash (thinking on) | 85.6 |
| gpt-oss-20b (high) | 84.8 |
| Mistral Small 3.1 24B (Non-reasoning) | 81.8 |
Earth science knowledge includes: 1,685 multiple-choice questions built on ESA's published question sets, one model call per question, checked by code. It is the knowledge part of the Earth science group of the Geospatial Intelligence Index, not part of the Geospatial Agent Index. See the methodology for how we run it.
All results
| Model | Score | Questions scored | Not scored (provider error) | Status | Cost per question | Time per question |
|---|---|---|---|---|---|---|
| Claude Opus 5.5 (high) | 95 | 1,685 of 1,685 | 0 | Counted | $0.0073 | 10s |
| Claude Opus 5.5 (xhigh) | 94 | 1,685 of 1,685 | 0 | Counted | $0.0084 | 10s |
| Claude Opus 5.5 (medium) | 94 | 1,685 of 1,685 | 0 | Counted | $0.012 | 14s |
| Claude Sonnet 5.5 (xhigh) | 94 | 1,685 of 1,685 | 0 | Counted | $0.0042 | 4s |
| Claude Sonnet 5.5 (high) | 94 | 1,685 of 1,685 | 0 | Counted | $0.0033 | 4s |
| Claude Sonnet 5.5 (medium) | 93 | 1,685 of 1,685 | 0 | Counted | $0.0054 | 3s |
| Claude Opus 4.8 (high) | 93 | 1,684 of 1,685 | 0 | Counted | $0.011 | 4s |
| Claude Opus 5 (high) | 93 | 1,685 of 1,685 | 0 | Counted | $0.012 | 4s |
| Claude Opus 4.7 (high) | 93 | 1,683 of 1,685 | 0 | Counted | $0.0085 | 2s |
| GPT-6.1 Sol (high) | 93 | 1,685 of 1,685 | 0 | Counted | $0.0019 | 13s |
| GPT-6.1 Sol (xhigh) | 93 | 1,685 of 1,685 | 0 | Counted | $0.0037 | 20s |
| GPT-6.1 Sol (medium) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0017 | 16s |
| DeepSeek V4 Pro (high) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0051 | 22s |
| Kimi K2.7 Code (always on) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0038 | 20s |
| Claude Haiku 5.5 (high) | 92 | 1,685 of 1,685 | 0 | Counted | $0.00034 | 4s |
| Kimi K3 (always on) | 92 | 1,685 of 1,685 | 0 | Counted | $0.020 | 50s |
| DeepSeek V4 Pro (max) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0051 | 40s |
| Claude Haiku 5.5 (xhigh) | 92 | 1,685 of 1,685 | 0 | Counted | $0.00040 | 4s |
| GLM-5.3 (max, default) | 92 | 1,685 of 1,685 | 0 | Counted | $0.010 | 35s |
| Kimi K2.6 (always on) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0086 | 47s |
| Claude Haiku 5.5 (medium) | 92 | 1,685 of 1,685 | 0 | Counted | $0.00043 | 4s |
| GLM-5.3-Flash (max) | 92 | 1,685 of 1,685 | 0 | Counted | $0.0010 | 51s |
| DeepSeek V4 Flash (max) | 91 | 1,685 of 1,685 | 0 | Counted | $0.0027 | 34s |
| Claude Sonnet 5 (high) | 91 | 1,684 of 1,685 | 0 | Counted | $0.0054 | 3s |
| GLM-5.2 (high) | 91 | 1,685 of 1,685 | 0 | Counted | $0.0052 | 14s |
| GPT-6 Luna (xhigh) | 91 | 1,685 of 1,685 | 0 | Counted | $0.00015 | 14s |
| DeepSeek V4 Flash (high) | 91 | 1,685 of 1,685 | 0 | Counted | $0.0013 | 22s |
| GLM-5.3 (low) | 91 | 1,685 of 1,685 | 0 | Counted | $0.00086 | 13s |
| Qwen 3.8 27B (xhigh) | 91 | 1,685 of 1,685 | 0 | Counted | $0.0037 | 46s |
| gpt-oss-120b (high) | 90 | 1,685 of 1,685 | 0 | Counted | $0.0011 | 19s |
| GLM-5.2 (none) | 89 | 1,685 of 1,685 | 0 | Counted | $0.0013 | 10s |
| Claude Haiku 4.5 (thinking 32k) | 89 | 1,685 of 1,685 | 0 | Counted | $0.0077 | 16s |
| GLM-5.2 (max) | 89 | 1,685 of 1,685 | 0 | Counted | $0.021 | 40s |
| Gemma 4 26B A4B (thinking on) | 89 | 1,685 of 1,685 | 0 | Counted | $0.0010 | 54s |
| gpt-oss-120b (low) | 88 | 1,685 of 1,685 | 0 | Counted | $0.00025 | 2s |
| GLM-4.7-Flash (thinking on) | 86 | 1,685 of 1,685 | 0 | Counted | $0.00082 | 52s |
| GLM-5.3-Flash (low) | 85 | 1,685 of 1,685 | 0 | Counted | $0.000087 | 38s |
| gpt-oss-20b (high) | 85 | 1,685 of 1,685 | 0 | Counted | $0.00049 | 16s |
| Mistral Small 3.1 24B (Non-reasoning) | 82 | 1,685 of 1,685 | 0 | Counted | $0.00028 | 7s |
| Claude Sonnet 4.6 (adaptive, effort high) | 98* | 840 of 1,685 | 0 | Stopped part-way | $0.014 | 13s |
| Claude Opus 4.6 (adaptive, effort high) | 98* | 946 of 1,685 | 0 | Stopped part-way, not in the index | $0.014 | 10s |
| Llama 3.3 70B (off) | 82 | 1,685 of 1,685 | 0 | Counted, not in the index | $0.00096 | 11s |
An asterisk marks a quiz that does not count yet. No quiz result: Llama 3.3 70B (Non-reasoning), Gemini 3.8 Flash (low), Gemini 3.1 Pro (preview) (high), Gemini 3.1 Pro (preview) (low), Gemini 3.1 Flash-Lite (low), Gemini 3.8 Flash (high), Gemini 3.1 Flash-Lite (minimal), Gemini 3.1 Flash-Lite (high).
Questions: the multiple-choice quiz sets of ESA Φ-lab's EVE (Earth Virtual Expert) project, eve-esa/mcqa-single-answer and eve-esa/mcqa-multiple-answers on Hugging Face, CC BY 4.0 (Atrio et al., "EVE: A Domain-Specific LLM Framework for Earth Intelligence", 2026). We dropped 7 items, each with its reason, and changed nothing else; the prompt wording around each question is ours. This site publishes scores only.