Benchmark Almanac

Earth-Bench

GPT-5 66% leads since September 2025
Not in model cards
Version 1

Agents analyze satellite observations with Earth science tools. The evaluator checks the final answer and compares tool calls with a reference sequence.

The authors test 248 tasks with prepared inputs. Agents either follow prescribed steps or plan their own workflow.

Released
September 2025
Kind
Apps and MCP servers
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
Interaction
Agentic
Environment
APIs and tools
Items from
Real work and use
Run by
Anyone
In views
Agents, Vision
Strongest model tested
GPT-5 #71 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
13
Entries in its paper, 10 models we track

GPT-5 leads with 66% among models released by September 2025 GPT-5 leads with 66% among models released by September 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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.

The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-5 Auto-planning 66%
  2. 2 Doubao-Seed-1.6 Instruction-following 59.5%
  3. 3 Kimi K2 Sep 2025, Instruction-following 56.7%
  4. 4 Gemini 2.5 Flash Sep 2025, Instruction-following 53%
  5. 5 DeepSeek-V3.1 Instruction-following 52.2%
  6. 6 Qwen3-Max-Preview Auto-planning 50.2%
  7. 7 GPT-4o (snapshot unspecified) Instruction-following 44.9%
  8. 8 Llama 4 Maverick Auto-planning 44.9%
  9. 9 Qwen Plus Apr 2025, Auto-planning 42.5%
  10. 10 GLM-4.5V Instruction-following 35.3%
  11. 11 Mistral-Large (snapshot unspecified) Auto-planning 30%
  12. 12 InternVL-3.5 Auto-planning 26.7%
  13. 13 Qwen3-32B Instruction-following 24.8%

Source: The Earth-Bench paper

#EntryScoreSettingDateSource
1 GPT-5 66% Auto-planning, Earth-Agent Aug 2025 Official leaderboard
2 Doubao-Seed-1.6 59.5% Instruction-following, Earth-Agent Jun 2025 Official leaderboard
3 Kimi K2 Sep 2025 56.7% Instruction-following, Earth-Agent Sep 2025 Official leaderboard
4 Gemini 2.5 Flash Sep 2025 53% Instruction-following, Earth-Agent Sep 2025 Official leaderboard
5 DeepSeek-V3.1 52.2% Instruction-following, Earth-Agent Aug 2025 Official leaderboard
6 Qwen3-Max-Preview 50.2% Auto-planning, Earth-Agent Sep 2025 Official leaderboard
7 GPT-4o (snapshot unspecified) 44.9% Instruction-following, Earth-Agent Official leaderboard
8 Llama 4 Maverick 44.9% Auto-planning, Earth-Agent Apr 2025 Official leaderboard
9 Qwen Plus Apr 2025 42.5% Auto-planning, Earth-Agent Apr 2025 Official leaderboard
10 GLM-4.5V 35.3% Instruction-following, Earth-Agent Aug 2025 Official leaderboard
11 Mistral-Large (snapshot unspecified) 30% Auto-planning, Earth-Agent Official leaderboard
12 InternVL-3.5 26.7% Auto-planning, Earth-Agent Official leaderboard
13 Qwen3-32B 24.8% Instruction-following, Earth-Agent Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5 66% Auto-planning, Earth-Agent Aug 2025 Official leaderboard
2 Doubao-Seed-1.6 59.5% Instruction-following, Earth-Agent Jun 2025 Official leaderboard
3 Kimi K2 Sep 2025 56.7% Instruction-following, Earth-Agent Sep 2025 Official leaderboard
4 Gemini 2.5 Flash Sep 2025 53% Instruction-following, Earth-Agent Sep 2025 Official leaderboard
5 DeepSeek-V3.1 52.2% Instruction-following, Earth-Agent Aug 2025 Official leaderboard
6 Qwen3-Max-Preview 50.2% Auto-planning, Earth-Agent Sep 2025 Official leaderboard
7 Llama 4 Maverick 44.9% Auto-planning, Earth-Agent Apr 2025 Official leaderboard
8 Qwen Plus Apr 2025 42.5% Auto-planning, Earth-Agent Apr 2025 Official leaderboard
9 GLM-4.5V 35.3% Instruction-following, Earth-Agent Aug 2025 Official leaderboard
10 Qwen3-32B 24.8% Instruction-following, Earth-Agent Apr 2025 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s paper: Spectrum, Products and RGB. Each ranks models on one part of the test. GPT-5 leads 2 of them, and Kimi K2 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Spectrum

10 models we track have a score here.

  1. 1 GPT-5 64%
  2. 2 Doubao-Seed-1.6 57%
  3. 3 Gemini 2.5 Flash Sep 2025 ↑1 52%
  4. 4 Kimi K2 Sep 2025 ↓1 50%
  5. 5 DeepSeek-V3.1 47%
  6. 6 Qwen3-Max-Preview 45%
  7. 7 Llama 4 Maverick 37%
  8. 8 Qwen Plus Apr 2025 36%
  9. 9 GLM-4.5V 33.3%
  10. 10 Qwen3-32B 29%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-5 Earth-Agent
Instruction… Auto-planni…
66%
Doubao-Seed-1.6 Earth-Agent
Auto-planni… Instruction…
59.5%
Kimi K2 Earth-Agent
Auto-planni… Instruction…
56.7%
Gemini 2.5 Flash Earth-Agent
Auto-planni…
53%
DeepSeek-V3.1 Earth-Agent
Auto-planni…
52.2%
Qwen3-Max-Preview Earth-Agent
Instruction…
50.2%
Llama 4 Maverick Earth-Agent
Instruction… Auto-planni…
44.9%
Qwen Plus Earth-Agent
Instruction… Auto-planni…
42.5%
GLM-4.5V Earth-Agent
Auto-planni…
35.3%
Qwen3-32B Earth-Agent
Auto-planni… Instruction…
24.8%

Source: The Earth-Bench paper

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5 Auto-planning Earth-Agent 66%
GPT-5 Instruction-following Earth-Agent 62.4%
Doubao-Seed-1.6 Instruction-following Earth-Agent 59.5%
Kimi K2 Sep 2025 Instruction-following Earth-Agent 56.7%
Gemini 2.5 Flash Sep 2025 Instruction-following Earth-Agent 53%
Doubao-Seed-1.6 Auto-planning Earth-Agent 52.5%
DeepSeek-V3.1 Instruction-following Earth-Agent 52.2%
Gemini 2.5 Flash Sep 2025 Auto-planning Earth-Agent 52.2%
DeepSeek-V3.1 Auto-planning Earth-Agent 51.4%
Kimi K2 Sep 2025 Auto-planning Earth-Agent 50.6%
Qwen3-Max-Preview Auto-planning Earth-Agent 50.2%
Qwen3-Max-Preview Instruction-following Earth-Agent 47.4%
Llama 4 Maverick Auto-planning Earth-Agent 44.9%
Qwen Plus Apr 2025 Auto-planning Earth-Agent 42.5%
Llama 4 Maverick Instruction-following Earth-Agent 38.5%
Qwen Plus Apr 2025 Instruction-following Earth-Agent 38.5%
GLM-4.5V Instruction-following Earth-Agent 35.3%
GLM-4.5V Auto-planning Earth-Agent 32.9%
Qwen3-32B Instruction-following Earth-Agent 24.8%
Qwen3-32B Auto-planning Earth-Agent 20.6%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-5 Earth-Agent
Instruction… Auto-planni…
66%
Doubao-Seed-1.6 Earth-Agent
Auto-planni… Instruction…
59.5%
Kimi K2 Earth-Agent
Auto-planni… Instruction…
56.7%
Gemini 2.5 Flash Earth-Agent
Auto-planni…
53%
DeepSeek-V3.1 Earth-Agent
Auto-planni…
52.2%
Qwen3-Max-Preview Earth-Agent
Instruction…
50.2%
Llama 4 Maverick Earth-Agent
Instruction… Auto-planni…
44.9%
Qwen Plus Earth-Agent
Instruction… Auto-planni…
42.5%
GLM-4.5V Earth-Agent
Auto-planni…
35.3%
Qwen3-32B Earth-Agent
Auto-planni… Instruction…
24.8%

Source: The Earth-Bench paper

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5 Auto-planning Earth-Agent 66%
GPT-5 Instruction-following Earth-Agent 62.4%
Doubao-Seed-1.6 Instruction-following Earth-Agent 59.5%
Kimi K2 Sep 2025 Instruction-following Earth-Agent 56.7%
Gemini 2.5 Flash Sep 2025 Instruction-following Earth-Agent 53%
Doubao-Seed-1.6 Auto-planning Earth-Agent 52.5%
DeepSeek-V3.1 Instruction-following Earth-Agent 52.2%
Gemini 2.5 Flash Sep 2025 Auto-planning Earth-Agent 52.2%
DeepSeek-V3.1 Auto-planning Earth-Agent 51.4%
Kimi K2 Sep 2025 Auto-planning Earth-Agent 50.6%
Qwen3-Max-Preview Auto-planning Earth-Agent 50.2%
Qwen3-Max-Preview Instruction-following Earth-Agent 47.4%
Llama 4 Maverick Auto-planning Earth-Agent 44.9%
Qwen Plus Apr 2025 Auto-planning Earth-Agent 42.5%
Llama 4 Maverick Instruction-following Earth-Agent 38.5%
Qwen Plus Apr 2025 Instruction-following Earth-Agent 38.5%
GLM-4.5V Instruction-following Earth-Agent 35.3%
GLM-4.5V Auto-planning Earth-Agent 32.9%
Qwen3-32B Instruction-following Earth-Agent 24.8%
Qwen3-32B Auto-planning Earth-Agent 20.6%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper Not tested since Sep 2025
GPT-5 66%

Source: The Earth-Bench paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 Doubao-Seed-1.6 Llama 4 Maverick 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 Doubao-Seed-1.6

Source: Official Earth-Bench 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

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

OpenAI Anthropic
Earth-Bench V2 2 leaders
Earth-Bench Not tested since Sep 2025
GPT-5 66%

Source: Official leaderboards

More in Tool use

All 265 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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (13 entries).
  • Pass Models scored 10 models we track, plus 3 other entries on its leaderboard.
  • Note Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. That’s expected for a test replaced by Earth-Bench V2.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
  • Pass Headroom The best is 66%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 20 rows for models we track and 3 other entries 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.

How we check