Spatial Agent Index v2
Version 2
Agents analyze geospatial files and produce numbers, maps, or lists. Axis Spatial averages the scores for each included evaluation.
Axis Spatial allows entries with a score on every included evaluation and at least 75% coverage. Code checks data outputs. A model grades maps.
- Made by
- Axis Spatial
- Released
- November 2026
- Kind
- Apps and MCP servers
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- In and out
- Text, Maps and geodata → Actions, Text, Maps and geodata
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- Spatial Agent Index v1
- In views
- Agents
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 86.0 Claude Opus 5.5 leads with 86.0
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
- 86.0 Claude Opus 5.5
- 82.0 GPT-6.1 Sol
- 81.0 Claude Fable 5.1
- 80.0 Claude Opus 5
- 80.0 GPT-6 Sol
- 79.0 Claude Sonnet 5.5
- 77.0 Claude Haiku 5.5
- 76.0 Claude Opus 4.8
- 76.0 GPT-5.6 Sol
- 76.0
DeepSeek V4.1 Flash
- 75.0 Kimi K3
- 74.0 Claude Opus 4.7
- 74.0 GLM-5.2
- 74.0 Claude Sonnet 5
- 74.0 GLM-5.3
- 73.0 GPT-5.6 Luna
- 73.0 GPT-6 Luna
- 72.0
DeepSeek-V4-Flash
- 72.0
DeepSeek-V4-Pro
- 72.0 Kimi K2.7 Code
- 72.0 GLM-5.3-Flash
- 72.0
Gemini 3.8 Flash
- 71.0 MiMo-V2.6 Flash
- 70.0 Kimi K2.6
- 69.0 GPT-5.6 Terra
- 69.0
Qwen 3.8 27B
- 68.0
MiniMax-M3
- 68.0
Nemotron 3 Ultra
- 64.0
Muse Glimmer
- 63.0
Mistral Large 4
- 60.0
Qwen 3.6 35B-A3B
- 58.0 Claude Haiku 4.5
- 56.0 Nemotron 3.5 Super 120B
- 56.0
Gemini 3.1 Flash-Lite
- 56.0
Gemma 4 26B A4B
- 55.0
Gemma 4 31B IT
- 53.0
MiniMax-M3.1-Flash
- 52.0
Step 5 Preview
- 52.0
Nemotron 3.5 Super VL
- 46.0 gpt-oss-120b
- 43.0 glm-4.7-flash
- 37.0
Laguna XS 2.1
- 33.0 gpt-oss-20b
- 33.0
Mistral Large 3
- 21.0
Nemotron 3 Nano Omni 30B-A3B
- 13.0
Nemotron 3.5 Lightning 30B-A3B
- 8.0
Llama 3.3 70B
- 4.0
Nemotron 3.5 Bolt E4B
- 1 Claude Opus 5.5 max 86.0
- 2 GPT-6.1 Sol xhigh 82.0
- 3 Claude Fable 5.1 medium 81.0
- 4 Claude Opus 5 high 80.0
- 5 GPT-6 Sol high 80.0
- 6 Claude Sonnet 5.5 max 79.0
- 7 Claude Haiku 5.5 max 77.0
- 8 Claude Opus 4.8 high 76.0
- 9 GPT-5.6 Sol high 76.0
- 10
DeepSeek V4.1 Flash max 76.0
- 11 Kimi K3 Reasoning 75.0
- 12 Claude Opus 4.7 high 74.0
- 13 GLM-5.2 max 74.0
- 14 Claude Sonnet 5 high 74.0
- 15 GLM-5.3 max 74.0
- 16 GPT-5.6 Luna xhigh 73.0
- 17 GPT-6 Luna xhigh 73.0
- 18
DeepSeek-V4-Flash high 72.0
- 19
DeepSeek-V4-Pro max 72.0
- 20 Kimi K2.7 Code Reasoning 72.0
- 21 GLM-5.3-Flash max 72.0
- 22
Gemini 3.8 Flash low 72.0
- 23 MiMo-V2.6 Flash Reasoning 71.0
- 24 Kimi K2.6 Reasoning 70.0
- 25 GPT-5.6 Terra high 69.0
- 26
Qwen 3.8 27B Reasoning 69.0
- 27
MiniMax-M3 Reasoning 68.0
- 28
Nemotron 3 Ultra high 68.0
- 29
Muse Glimmer high 64.0
- 30
Mistral Large 4 high 63.0
- 31
Qwen 3.6 35B-A3B Reasoning 60.0
- 32 Claude Haiku 4.5 Reasoning 58.0
- 33 Nemotron 3.5 Super 120B Reasoning 56.0
- 34
Gemini 3.1 Flash-Lite high 56.0
- 35
Gemma 4 26B A4B Reasoning 56.0
- 36
Gemma 4 31B IT Reasoning 55.0
- 37
MiniMax-M3.1-Flash max 53.0
- 38
Step 5 Preview Reasoning 52.0
- 39
Nemotron 3.5 Super VL Reasoning 52.0
- 40 gpt-oss-120b high 46.0
- 41 glm-4.7-flash Reasoning 43.0
- 42
Laguna XS 2.1 Reasoning 37.0
- 43 gpt-oss-20b high 33.0
- 44
Mistral Large 3 Non-reasoning 33.0
- 45
Nemotron 3 Nano Omni 30B-A3B Reasoning 21.0
- 46
Nemotron 3.5 Lightning 30B-A3B Reasoning 13.0
- 47
Llama 3.3 70B Non-reasoning 8.0
- 48
Nemotron 3.5 Bolt E4B Reasoning 4.0
Source: Official Spatial Agent Index v2 leaderboard
- 86.0 Claude Opus 5.5
- 82.0 GPT-6.1 Sol
- 81.0 Claude Fable 5.1
- 80.0 Claude Opus 5
- 80.0 GPT-6 Sol
- 79.0 Claude Sonnet 5.5
- 77.0 Claude Haiku 5.5
- 76.0 Claude Opus 4.8
- 76.0 GPT-5.6 Sol
- 76.0
DeepSeek V4.1 Flash
- 75.0 Kimi K3
- 74.0 Claude Opus 4.7
- 74.0 GLM-5.2
- 74.0 Claude Sonnet 5
- 74.0 GLM-5.3
- 73.0 GPT-5.6 Luna
- 73.0 GPT-6 Luna
- 72.0
DeepSeek-V4-Flash
- 72.0
DeepSeek-V4-Pro
- 72.0 Kimi K2.7 Code
- 72.0 GLM-5.3-Flash
- 72.0
Gemini 3.8 Flash
- 71.0 MiMo-V2.6 Flash
- 70.0 Kimi K2.6
- 69.0 GPT-5.6 Terra
- 69.0
Qwen 3.8 27B
- 68.0
MiniMax-M3
- 68.0
Nemotron 3 Ultra
- 64.0
Muse Glimmer
- 63.0
Mistral Large 4
- 60.0
Qwen 3.6 35B-A3B
- 58.0 Claude Haiku 4.5
- 56.0
Gemini 3.1 Flash-Lite
- 56.0
Gemma 4 26B A4B
- 55.0
Gemma 4 31B IT
- 53.0
MiniMax-M3.1-Flash
- 52.0
Step 5 Preview
- 52.0
Nemotron 3.5 Super VL
- 46.0 gpt-oss-120b
- 43.0 glm-4.7-flash
- 37.0
Laguna XS 2.1
- 33.0 gpt-oss-20b
- 33.0
Mistral Large 3
- 21.0
Nemotron 3 Nano Omni 30B-A3B
- 13.0
Nemotron 3.5 Lightning 30B-A3B
- 8.0
Llama 3.3 70B
- 4.0
Nemotron 3.5 Bolt E4B
- 1 Claude Opus 5.5 max 86.0
- 2 GPT-6.1 Sol xhigh 82.0
- 3 Claude Fable 5.1 medium 81.0
- 4 Claude Opus 5 high 80.0
- 5 GPT-6 Sol high 80.0
- 6 Claude Sonnet 5.5 max 79.0
- 7 Claude Haiku 5.5 max 77.0
- 8 Claude Opus 4.8 high 76.0
- 9 GPT-5.6 Sol high 76.0
- 10
DeepSeek V4.1 Flash max 76.0
- 11 Kimi K3 Reasoning 75.0
- 12 Claude Opus 4.7 high 74.0
- 13 GLM-5.2 max 74.0
- 14 Claude Sonnet 5 high 74.0
- 15 GLM-5.3 max 74.0
- 16 GPT-5.6 Luna xhigh 73.0
- 17 GPT-6 Luna xhigh 73.0
- 18
DeepSeek-V4-Flash high 72.0
- 19
DeepSeek-V4-Pro max 72.0
- 20 Kimi K2.7 Code Reasoning 72.0
- 21 GLM-5.3-Flash max 72.0
- 22
Gemini 3.8 Flash low 72.0
- 23 MiMo-V2.6 Flash Reasoning 71.0
- 24 Kimi K2.6 Reasoning 70.0
- 25 GPT-5.6 Terra high 69.0
- 26
Qwen 3.8 27B Reasoning 69.0
- 27
MiniMax-M3 Reasoning 68.0
- 28
Nemotron 3 Ultra high 68.0
- 29
Muse Glimmer high 64.0
- 30
Mistral Large 4 high 63.0
- 31
Qwen 3.6 35B-A3B Reasoning 60.0
- 32 Claude Haiku 4.5 Reasoning 58.0
- 33
Gemini 3.1 Flash-Lite high 56.0
- 34
Gemma 4 26B A4B Reasoning 56.0
- 35
Gemma 4 31B IT Reasoning 55.0
- 36
MiniMax-M3.1-Flash max 53.0
- 37
Step 5 Preview Reasoning 52.0
- 38
Nemotron 3.5 Super VL Reasoning 52.0
- 39 gpt-oss-120b high 46.0
- 40 glm-4.7-flash Reasoning 43.0
- 41
Laguna XS 2.1 Reasoning 37.0
- 42 gpt-oss-20b high 33.0
- 43
Mistral Large 3 Non-reasoning 33.0
- 44
Nemotron 3 Nano Omni 30B-A3B Reasoning 21.0
- 45
Nemotron 3.5 Lightning 30B-A3B Reasoning 13.0
- 46
Llama 3.3 70B Non-reasoning 8.0
- 47
Nemotron 3.5 Bolt E4B Reasoning 4.0
Source: Official Spatial Agent Index v2 leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 86.0 | max, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 2 | GPT-6.1 Sol | 82.0 | xhigh, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 3 | Claude Fable 5.1 | 81.0 | medium, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 4 | Claude Opus 5 | 80.0 | high, Claude Code | Jul 2026 | axisspatial.com | Official leaderboard |
| 5 | GPT-6 Sol | 80.0 | high, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 6 | Claude Sonnet 5.5 | 79.0 | max, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 7 | Claude Haiku 5.5 | 77.0 | max, Claude Code | Oct 2026 | axisspatial.com | Official leaderboard |
| 8 | Claude Opus 4.8 | 76.0 | high, Claude Code | May 2026 | axisspatial.com | Official leaderboard |
| 9 | GPT-5.6 Sol | 76.0 | high, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 10 | | 76.0 | max, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 11 | Kimi K3 | 75.0 | Reasoning, Kimi Code | Jul 2026 | axisspatial.com | Official leaderboard |
| 12 | Claude Opus 4.7 | 74.0 | high, Claude Code | Apr 2026 | axisspatial.com | Official leaderboard |
| 13 | GLM-5.2 | 74.0 | max, Claude Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 14 | Claude Sonnet 5 | 74.0 | high, Claude Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 15 | GLM-5.3 | 74.0 | max, Claude Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 16 | GPT-5.6 Luna | 73.0 | xhigh, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 17 | GPT-6 Luna | 73.0 | xhigh, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 18 | | 72.0 | high, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 19 | | 72.0 | max, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 20 | Kimi K2.7 Code | 72.0 | Reasoning, Kimi Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 21 | GLM-5.3-Flash | 72.0 | max, Claude Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 22 | | 72.0 | low, Terminus-2 | Sep 2026 | axisspatial.com | Official leaderboard |
| 23 | MiMo-V2.6 Flash | 71.0 | Reasoning, MiMo Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 24 | Kimi K2.6 | 70.0 | Reasoning, Kimi Code | Apr 2026 | axisspatial.com | Official leaderboard |
| 25 | GPT-5.6 Terra | 69.0 | high, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 26 | | 69.0 | Reasoning, Qwen Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 27 | | 68.0 | Reasoning, MiniMax Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 28 | | 68.0 | high, Terminus-2 | Jun 2026 | axisspatial.com | Official leaderboard |
| 29 | | 64.0 | high, Terminus-2 | Aug 2026 | axisspatial.com | Official leaderboard |
| 30 | | 63.0 | high, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 31 | | 60.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 32 | Claude Haiku 4.5 | 58.0 | Reasoning, Claude Code | Oct 2025 | axisspatial.com | Official leaderboard |
| 33 | Nemotron 3.5 Super 120B | 56.0 | Reasoning, Terminus-2 | axisspatial.com | Official leaderboard | |
| 34 | | 56.0 | high, Terminus-2 | Mar 2026 | axisspatial.com | Official leaderboard |
| 35 | | 56.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 36 | | 55.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 37 | | 53.0 | max, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 38 | | 52.0 | Reasoning, Terminus-2 | Sep 2026 | axisspatial.com | Official leaderboard |
| 39 | | 52.0 | Reasoning, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 40 | gpt-oss-120b | 46.0 | high, Terminus-2 | Aug 2025 | axisspatial.com | Official leaderboard |
| 41 | glm-4.7-flash | 43.0 | Reasoning, Terminus-2 | Jan 2026 | axisspatial.com | Official leaderboard |
| 42 | | 37.0 | Reasoning, Terminus-2 | Jul 2026 | axisspatial.com | Official leaderboard |
| 43 | gpt-oss-20b | 33.0 | high, Terminus-2 | Aug 2025 | axisspatial.com | Official leaderboard |
| 44 | | 33.0 | Non-reasoning, Terminus-2 | Dec 2025 | axisspatial.com | Official leaderboard |
| 45 | | 21.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 46 | | 13.0 | Reasoning, Terminus-2 | Aug 2026 | axisspatial.com | Official leaderboard |
| 47 | | 8.0 | Non-reasoning, Terminus-2 | Dec 2024 | axisspatial.com | Official leaderboard |
| 48 | | 4.0 | Reasoning, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 86.0 | max, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 2 | GPT-6.1 Sol | 82.0 | xhigh, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 3 | Claude Fable 5.1 | 81.0 | medium, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 4 | Claude Opus 5 | 80.0 | high, Claude Code | Jul 2026 | axisspatial.com | Official leaderboard |
| 5 | GPT-6 Sol | 80.0 | high, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 6 | Claude Sonnet 5.5 | 79.0 | max, Claude Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 7 | Claude Haiku 5.5 | 77.0 | max, Claude Code | Oct 2026 | axisspatial.com | Official leaderboard |
| 8 | Claude Opus 4.8 | 76.0 | high, Claude Code | May 2026 | axisspatial.com | Official leaderboard |
| 9 | GPT-5.6 Sol | 76.0 | high, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 10 | | 76.0 | max, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 11 | Kimi K3 | 75.0 | Reasoning, Kimi Code | Jul 2026 | axisspatial.com | Official leaderboard |
| 12 | Claude Opus 4.7 | 74.0 | high, Claude Code | Apr 2026 | axisspatial.com | Official leaderboard |
| 13 | GLM-5.2 | 74.0 | max, Claude Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 14 | Claude Sonnet 5 | 74.0 | high, Claude Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 15 | GLM-5.3 | 74.0 | max, Claude Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 16 | GPT-5.6 Luna | 73.0 | xhigh, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 17 | GPT-6 Luna | 73.0 | xhigh, Codex | Sep 2026 | axisspatial.com | Official leaderboard |
| 18 | | 72.0 | high, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 19 | | 72.0 | max, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 20 | Kimi K2.7 Code | 72.0 | Reasoning, Kimi Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 21 | GLM-5.3-Flash | 72.0 | max, Claude Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 22 | | 72.0 | low, Terminus-2 | Sep 2026 | axisspatial.com | Official leaderboard |
| 23 | MiMo-V2.6 Flash | 71.0 | Reasoning, MiMo Code | Sep 2026 | axisspatial.com | Official leaderboard |
| 24 | Kimi K2.6 | 70.0 | Reasoning, Kimi Code | Apr 2026 | axisspatial.com | Official leaderboard |
| 25 | GPT-5.6 Terra | 69.0 | high, Codex | Jul 2026 | axisspatial.com | Official leaderboard |
| 26 | | 69.0 | Reasoning, Qwen Code | Aug 2026 | axisspatial.com | Official leaderboard |
| 27 | | 68.0 | Reasoning, MiniMax Code | Jun 2026 | axisspatial.com | Official leaderboard |
| 28 | | 68.0 | high, Terminus-2 | Jun 2026 | axisspatial.com | Official leaderboard |
| 29 | | 64.0 | high, Terminus-2 | Aug 2026 | axisspatial.com | Official leaderboard |
| 30 | | 63.0 | high, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 31 | | 60.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 32 | Claude Haiku 4.5 | 58.0 | Reasoning, Claude Code | Oct 2025 | axisspatial.com | Official leaderboard |
| 33 | | 56.0 | high, Terminus-2 | Mar 2026 | axisspatial.com | Official leaderboard |
| 34 | | 56.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 35 | | 55.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 36 | | 53.0 | max, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 37 | | 52.0 | Reasoning, Terminus-2 | Sep 2026 | axisspatial.com | Official leaderboard |
| 38 | | 52.0 | Reasoning, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
| 39 | gpt-oss-120b | 46.0 | high, Terminus-2 | Aug 2025 | axisspatial.com | Official leaderboard |
| 40 | glm-4.7-flash | 43.0 | Reasoning, Terminus-2 | Jan 2026 | axisspatial.com | Official leaderboard |
| 41 | | 37.0 | Reasoning, Terminus-2 | Jul 2026 | axisspatial.com | Official leaderboard |
| 42 | gpt-oss-20b | 33.0 | high, Terminus-2 | Aug 2025 | axisspatial.com | Official leaderboard |
| 43 | | 33.0 | Non-reasoning, Terminus-2 | Dec 2025 | axisspatial.com | Official leaderboard |
| 44 | | 21.0 | Reasoning, Terminus-2 | Apr 2026 | axisspatial.com | Official leaderboard |
| 45 | | 13.0 | Reasoning, Terminus-2 | Aug 2026 | axisspatial.com | Official leaderboard |
| 46 | | 8.0 | Non-reasoning, Terminus-2 | Dec 2024 | axisspatial.com | Official leaderboard |
| 47 | | 4.0 | Reasoning, Terminus-2 | Oct 2026 | axisspatial.com | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Earth-Bench V2, GeoBenchX and GS-QA2. Claude Opus 5.5 leads 3 of them, and GPT-6.1 Sol leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Earth-Bench V2
47 models we track have a score here.
- 1 Claude Opus 5.5 80.0
- 2 GLM-5.3 ↑13 77.0
- 3
DeepSeek V4.1 Flash ↑7 77.0
- 4 Kimi K3 ↑7 75.0
- 5 GPT-6 Sol 75.0
- 6 Claude Opus 5 ↓2 74.0
- 7
DeepSeek-V4-Flash ↑11 73.0
- 8 Kimi K2.7 Code ↑12 73.0
- 9 Claude Fable 5.1 ↓6 73.0
- 10 GPT-6.1 Sol ↓8 72.0
GeoBenchX
47 models we track have a score here.
- 1 Claude Opus 5.5 84.0
- 2 Claude Fable 5.1 ↑1 81.0
- 3 Claude Sonnet 5.5 ↑3 81.0
- 4 GPT-6.1 Sol ↓2 79.0
- 5 Claude Haiku 5.5 ↑2 78.0
- 6 Claude Sonnet 5 ↑8 77.0
- 7
Gemini 3.8 Flash ↑15 76.0
- 8 Claude Opus 5 ↓4 75.0
- 9 GPT-6 Sol ↓4 75.0
- 10 GPT-6 Luna ↑7 74.0
GS-QA2
47 models we track have a score here.
- 1 Claude Opus 5.5 94.0
- 2 GPT-6.1 Sol 94.0
- 3 Claude Sonnet 5.5 ↑3 92.0
- 4 Claude Opus 5 91.0
- 5 Claude Fable 5.1 ↓2 90.0
- 6
DeepSeek V4.1 Flash ↑4 89.0
- 7 GPT-6 Sol ↓2 89.0
- 8 GPT-5.6 Sol ↑1 87.0
- 9 Claude Haiku 5.5 ↓2 87.0
- 10
Gemini 3.8 Flash ↑12 86.0
Vision agents
21 models we track have a score here.
- 1 GPT-6.1 Sol ↑1 90.0
- 2 Claude Opus 5.5 ↓1 89.0
- 3 Claude Fable 5.1 88.0
- 4 Claude Sonnet 5.5 ↑2 83.0
- 5 GLM-5.3-Flash ↑16 81.0
- 6
DeepSeek V4.1 Flash ↑4 80.0
- 7 GPT-6 Sol ↓2 80.0
- 8 Claude Opus 5 ↓4 77.0
- 9 GPT-5.6 Sol 75.0
- 10 Claude Haiku 5.5 ↓3 75.0
The best score, 86.0, costs $1.14 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at medium comes within 4 of the best for $0.05 a task, 25 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Spatial Agent Index v2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 86.0 | $1.14 | 29,000 |
| Claude Opus 5.5 | xhigh | Claude Code | 85.0 | $0.25 | 5,000 |
| Claude Opus 5.5 | high | Claude Code | 82.0 | $0.13 | 2,000 |
| GPT-6.1 Sol | xhigh | Codex | 82.0 | $0.09 | 3,000 |
| GPT-6.1 Sol | medium | Codex | 82.0 | $0.05 | 1,000 |
| Claude Fable 5.1 | medium | Claude Code | 81.0 | $0.33 | 2,000 |
| Claude Opus 5 | high | Claude Code | 80.0 | $0.32 | 4,000 |
| Claude Fable 5.1 | high | Claude Code | 80.0 | $0.44 | 3,000 |
| Claude Opus 5.5 | medium | Claude Code | 80.0 | $0.11 | 2,000 |
| GPT-6 Sol | high | Codex | 80.0 | $0.08 | 3,000 |
| GPT-6.1 Sol | high | Codex | 80.0 | $0.06 | 2,000 |
| Claude Sonnet 5.5 | max | Claude Code | 79.0 | $0.98 | 52,000 |
| Claude Sonnet 5.5 | xhigh | Claude Code | 79.0 | $0.11 | 4,000 |
| Claude Sonnet 5.5 | high | Claude Code | 78.0 | $0.06 | 2,000 |
| Claude Haiku 5.5 | max | Claude Code | 77.0 | $0.09 | 45,000 |
| Claude Opus 4.8 | high | Claude Code | 76.0 | $0.26 | 4,000 |
| GPT-5.6 Sol | high | Codex | 76.0 | $0.21 | 4,000 |
| max | Codex | 76.0 | $0.08 | 41,000 | |
| max | Claude Code | 76.0 | $0.20 | 48,000 | |
| Claude Haiku 5.5 | xhigh | Claude Code | 76.0 | $0.02 | 12,000 |
| Claude Haiku 5.5 | high | Claude Code | 76.0 | $0.009 | 6,000 |
| Kimi K3 | Reasoning | Kimi Code | 75.0 | $0.32 | 9,000 |
| Claude Opus 4.7 | high | Claude Code | 74.0 | $0.34 | 4,000 |
| GLM-5.2 | max | Claude Code | 74.0 | $0.34 | 28,000 |
| Claude Sonnet 5 | high | Claude Code | 74.0 | $0.20 | 6,000 |
| GLM-5.3 | max | Claude Code | 74.0 | $0.48 | 15,000 |
| Claude Opus 5.5 | low | Claude Code | 74.0 | $0.08 | 1,000 |
| GPT-5.6 Luna | xhigh | Codex | 73.0 | $0.02 | 7,000 |
| Kimi K3 | Reasoning | Terminus-2 | 73.0 | $0.23 | 6,000 |
| GPT-6 Luna | xhigh | Codex | 73.0 | $0.007 | 6,000 |
| high | Terminus-2 | 72.0 | $0.07 | 31,000 | |
| max | Terminus-2 | 72.0 | $0.35 | 24,000 | |
| Kimi K2.7 Code | Reasoning | Kimi Code | 72.0 | $0.18 | 11,000 |
| Kimi K2.7 Code | Reasoning | Terminus-2 | 72.0 | $0.11 | 12,000 |
| GLM-5.2 | max | Terminus-2 | 72.0 | $0.32 | 30,000 |
| GPT-5.6 Luna | high | Codex | 72.0 | $0.02 | 5,000 |
| GLM-5.3 | max | Terminus-2 | 72.0 | $0.38 | 19,000 |
| GLM-5.3-Flash | max | Claude Code | 72.0 | $0.09 | 29,000 |
| low | Terminus-2 | 72.0 | $0.11 | 8,000 | |
| Claude Haiku 5.5 | medium | Claude Code | 72.0 | $0.006 | 4,000 |
| GLM-5.2 | high | Terminus-2 | 71.0 | $0.22 | 22,000 |
| MiMo-V2.6 Flash | Reasoning | MiMo Code | 71.0 | $0.05 | 32,000 |
| GPT-6 Luna | high | Codex | 71.0 | $0.004 | 3,000 |
| Claude Sonnet 5.5 | medium | Claude Code | 71.0 | $0.05 | 1,000 |
| Kimi K2.6 | Reasoning | Kimi Code | 70.0 | $0.27 | 18,000 |
| Kimi K2.6 | Reasoning | Terminus-2 | 70.0 | $0.09 | 12,000 |
| high | Terminus-2 | 70.0 | $0.30 | 20,000 | |
| Claude Haiku 5.5 | low | Claude Code | 70.0 | $0.005 | 3,000 |
| max | Terminus-2 | 69.0 | $0.06 | 29,000 | |
| GPT-5.6 Terra | high | Codex | 69.0 | $0.10 | 3,000 |
| Reasoning | Qwen Code | 69.0 | $0.22 | 28,000 | |
| Claude Sonnet 5.5 | low | Claude Code | 69.0 | $0.04 | 1,000 |
| Reasoning | MiniMax Code | 68.0 | $0.15 | 30,000 | |
| high | Terminus-2 | 68.0 | $0.08 | 9,000 | |
| GLM-5.3 | low | Terminus-2 | 68.0 | $0.27 | 10,000 |
| xhigh | Terminus-2 | 67.0 | $0.12 | 22,000 | |
| high | Codex | 66.0 | $0.09 | 19,000 | |
| GPT-5.6 Luna | medium | Codex | 66.0 | $0.009 | 3,000 |
| high | Terminus-2 | 64.0 | $0.08 | 11,000 | |
| GLM-5.2 | Non-reasoning | Terminus-2 | 63.0 | $0.10 | 6,000 |
| GLM-5.3-Flash | low | Terminus-2 | 63.0 | $0.05 | 15,000 |
| GLM-5.3-Flash | max | Terminus-2 | 63.0 | $0.09 | 30,000 |
| high | Terminus-2 | 63.0 | $0.10 | 14,000 | |
| GPT-5.6 Luna | low | Codex | 61.0 | $0.006 | 2,000 |
| Reasoning | Terminus-2 | 60.0 | $0.07 | 16,000 | |
| high | Claude Code | 59.0 | $0.08 | 19,000 | |
| Claude Haiku 4.5 | Reasoning | Claude Code | 58.0 | $0.09 | 7,000 |
| Reasoning | Qwen Code | 57.0 | 18,000 | ||
| GPT-6 Luna | medium | Codex | 57.0 | $0.003 | 1,000 |
| high | Terminus-2 | 56.0 | $0.03 | 16,000 | |
| Reasoning | Terminus-2 | 56.0 | $0.02 | 21,000 | |
| Reasoning | Terminus-2 | 55.0 | $0.02 | 8,000 | |
| max | Terminus-2 | 53.0 | $0.02 | 19,000 | |
| Reasoning | Terminus-2 | 52.0 | $0.13 | 24,000 | |
| Reasoning | Terminus-2 | 52.0 | $0.01 | 7,000 | |
| GPT-6 Luna | low | Codex | 51.0 | $0.003 | 1,000 |
| low | Terminus-2 | 48.0 | $0.02 | 8,000 | |
| gpt-oss-120b | high | Terminus-2 | 46.0 | $0.03 | 15,000 |
| gpt-oss-120b | high | Codex | 43.0 | $0.26 | 27,000 |
| glm-4.7-flash | Reasoning | Terminus-2 | 43.0 | $0.04 | 14,000 |
| glm-4.7-flash | Reasoning | Claude Code | 41.0 | $0.27 | 15,000 |
| Reasoning | Terminus-2 | 37.0 | $0.05 | 24,000 | |
| gpt-oss-20b | high | Terminus-2 | 33.0 | $0.02 | 40,000 |
| Non-reasoning | Terminus-2 | 33.0 | $0.03 | 4,000 | |
| minimal | Terminus-2 | 32.0 | $0.007 | 2,000 | |
| gpt-oss-120b | low | Terminus-2 | 31.0 | $0.005 | 2,000 |
| Reasoning | Terminus-2 | 21.0 | 21,000 | ||
| Reasoning | Terminus-2 | 13.0 | $0.01 | 7,000 | |
| gpt-oss-20b | high | Codex | 9.0 | $0.09 | 23,000 |
| Non-reasoning | Terminus-2 | 8.0 | $0.02 | 2,000 | |
| Reasoning | Terminus-2 | 4.0 | 14,000 |
The best score, 86.0, costs $1.14 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at medium comes within 4 of the best for $0.05 a task, 25 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Spatial Agent Index v2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 86.0 | $1.14 | 29,000 |
| Claude Opus 5.5 | xhigh | Claude Code | 85.0 | $0.25 | 5,000 |
| Claude Opus 5.5 | high | Claude Code | 82.0 | $0.13 | 2,000 |
| GPT-6.1 Sol | xhigh | Codex | 82.0 | $0.09 | 3,000 |
| GPT-6.1 Sol | medium | Codex | 82.0 | $0.05 | 1,000 |
| Claude Fable 5.1 | medium | Claude Code | 81.0 | $0.33 | 2,000 |
| Claude Opus 5 | high | Claude Code | 80.0 | $0.32 | 4,000 |
| Claude Fable 5.1 | high | Claude Code | 80.0 | $0.44 | 3,000 |
| Claude Opus 5.5 | medium | Claude Code | 80.0 | $0.11 | 2,000 |
| GPT-6 Sol | high | Codex | 80.0 | $0.08 | 3,000 |
| GPT-6.1 Sol | high | Codex | 80.0 | $0.06 | 2,000 |
| Claude Sonnet 5.5 | max | Claude Code | 79.0 | $0.98 | 52,000 |
| Claude Sonnet 5.5 | xhigh | Claude Code | 79.0 | $0.11 | 4,000 |
| Claude Sonnet 5.5 | high | Claude Code | 78.0 | $0.06 | 2,000 |
| Claude Haiku 5.5 | max | Claude Code | 77.0 | $0.09 | 45,000 |
| Claude Opus 4.8 | high | Claude Code | 76.0 | $0.26 | 4,000 |
| GPT-5.6 Sol | high | Codex | 76.0 | $0.21 | 4,000 |
| max | Codex | 76.0 | $0.08 | 41,000 | |
| max | Claude Code | 76.0 | $0.20 | 48,000 | |
| Claude Haiku 5.5 | xhigh | Claude Code | 76.0 | $0.02 | 12,000 |
| Claude Haiku 5.5 | high | Claude Code | 76.0 | $0.009 | 6,000 |
| Kimi K3 | Reasoning | Kimi Code | 75.0 | $0.32 | 9,000 |
| Claude Opus 4.7 | high | Claude Code | 74.0 | $0.34 | 4,000 |
| GLM-5.2 | max | Claude Code | 74.0 | $0.34 | 28,000 |
| Claude Sonnet 5 | high | Claude Code | 74.0 | $0.20 | 6,000 |
| GLM-5.3 | max | Claude Code | 74.0 | $0.48 | 15,000 |
| Claude Opus 5.5 | low | Claude Code | 74.0 | $0.08 | 1,000 |
| GPT-5.6 Luna | xhigh | Codex | 73.0 | $0.02 | 7,000 |
| Kimi K3 | Reasoning | Terminus-2 | 73.0 | $0.23 | 6,000 |
| GPT-6 Luna | xhigh | Codex | 73.0 | $0.007 | 6,000 |
| high | Terminus-2 | 72.0 | $0.07 | 31,000 | |
| max | Terminus-2 | 72.0 | $0.35 | 24,000 | |
| Kimi K2.7 Code | Reasoning | Kimi Code | 72.0 | $0.18 | 11,000 |
| Kimi K2.7 Code | Reasoning | Terminus-2 | 72.0 | $0.11 | 12,000 |
| GLM-5.2 | max | Terminus-2 | 72.0 | $0.32 | 30,000 |
| GPT-5.6 Luna | high | Codex | 72.0 | $0.02 | 5,000 |
| GLM-5.3 | max | Terminus-2 | 72.0 | $0.38 | 19,000 |
| GLM-5.3-Flash | max | Claude Code | 72.0 | $0.09 | 29,000 |
| low | Terminus-2 | 72.0 | $0.11 | 8,000 | |
| Claude Haiku 5.5 | medium | Claude Code | 72.0 | $0.006 | 4,000 |
| GLM-5.2 | high | Terminus-2 | 71.0 | $0.22 | 22,000 |
| MiMo-V2.6 Flash | Reasoning | MiMo Code | 71.0 | $0.05 | 32,000 |
| GPT-6 Luna | high | Codex | 71.0 | $0.004 | 3,000 |
| Claude Sonnet 5.5 | medium | Claude Code | 71.0 | $0.05 | 1,000 |
| Kimi K2.6 | Reasoning | Kimi Code | 70.0 | $0.27 | 18,000 |
| Kimi K2.6 | Reasoning | Terminus-2 | 70.0 | $0.09 | 12,000 |
| high | Terminus-2 | 70.0 | $0.30 | 20,000 | |
| Claude Haiku 5.5 | low | Claude Code | 70.0 | $0.005 | 3,000 |
| max | Terminus-2 | 69.0 | $0.06 | 29,000 | |
| GPT-5.6 Terra | high | Codex | 69.0 | $0.10 | 3,000 |
| Reasoning | Qwen Code | 69.0 | $0.22 | 28,000 | |
| Claude Sonnet 5.5 | low | Claude Code | 69.0 | $0.04 | 1,000 |
| Reasoning | MiniMax Code | 68.0 | $0.15 | 30,000 | |
| high | Terminus-2 | 68.0 | $0.08 | 9,000 | |
| GLM-5.3 | low | Terminus-2 | 68.0 | $0.27 | 10,000 |
| xhigh | Terminus-2 | 67.0 | $0.12 | 22,000 | |
| high | Codex | 66.0 | $0.09 | 19,000 | |
| GPT-5.6 Luna | medium | Codex | 66.0 | $0.009 | 3,000 |
| high | Terminus-2 | 64.0 | $0.08 | 11,000 | |
| GLM-5.2 | Non-reasoning | Terminus-2 | 63.0 | $0.10 | 6,000 |
| GLM-5.3-Flash | low | Terminus-2 | 63.0 | $0.05 | 15,000 |
| GLM-5.3-Flash | max | Terminus-2 | 63.0 | $0.09 | 30,000 |
| high | Terminus-2 | 63.0 | $0.10 | 14,000 | |
| GPT-5.6 Luna | low | Codex | 61.0 | $0.006 | 2,000 |
| Reasoning | Terminus-2 | 60.0 | $0.07 | 16,000 | |
| high | Claude Code | 59.0 | $0.08 | 19,000 | |
| Claude Haiku 4.5 | Reasoning | Claude Code | 58.0 | $0.09 | 7,000 |
| Reasoning | Qwen Code | 57.0 | 18,000 | ||
| GPT-6 Luna | medium | Codex | 57.0 | $0.003 | 1,000 |
| high | Terminus-2 | 56.0 | $0.03 | 16,000 | |
| Reasoning | Terminus-2 | 56.0 | $0.02 | 21,000 | |
| Reasoning | Terminus-2 | 55.0 | $0.02 | 8,000 | |
| max | Terminus-2 | 53.0 | $0.02 | 19,000 | |
| Reasoning | Terminus-2 | 52.0 | $0.13 | 24,000 | |
| Reasoning | Terminus-2 | 52.0 | $0.01 | 7,000 | |
| GPT-6 Luna | low | Codex | 51.0 | $0.003 | 1,000 |
| low | Terminus-2 | 48.0 | $0.02 | 8,000 | |
| gpt-oss-120b | high | Terminus-2 | 46.0 | $0.03 | 15,000 |
| gpt-oss-120b | high | Codex | 43.0 | $0.26 | 27,000 |
| glm-4.7-flash | Reasoning | Terminus-2 | 43.0 | $0.04 | 14,000 |
| glm-4.7-flash | Reasoning | Claude Code | 41.0 | $0.27 | 15,000 |
| Reasoning | Terminus-2 | 37.0 | $0.05 | 24,000 | |
| gpt-oss-20b | high | Terminus-2 | 33.0 | $0.02 | 40,000 |
| Non-reasoning | Terminus-2 | 33.0 | $0.03 | 4,000 | |
| minimal | Terminus-2 | 32.0 | $0.007 | 2,000 | |
| gpt-oss-120b | low | Terminus-2 | 31.0 | $0.005 | 2,000 |
| Reasoning | Terminus-2 | 21.0 | 21,000 | ||
| Reasoning | Terminus-2 | 13.0 | $0.01 | 7,000 | |
| gpt-oss-20b | high | Codex | 9.0 | $0.09 | 23,000 |
| Non-reasoning | Terminus-2 | 8.0 | $0.02 | 2,000 | |
| Reasoning | Terminus-2 | 4.0 | 14,000 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Spatial Agent Index v2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Spatial Agent Index v2 leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
Versions
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Neon 56.3%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state.
Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (48 entries).
- Pass Models scored 47 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from October 2026, for Nemotron 3.5 Bolt E4B.
- Pass Frontier models 4 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Note Headroom Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on axisspatial.com: 91 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.