RL Environments and the Hierarchy of Agentic Capabilities
Our RL environment run on 9 models revealed the core capabilities all agents need to master: tool use, planning, adaptability, groundedness, and common sense.
Professional Graphical Reasoning
Chartography
Chartography is our benchmark for professional chart understanding. It tests whether frontier models can read the Kaplan-Meier curves, candlestick charts, contour maps, Sankey diagrams, Bode plots, and other specialized graphics that professionals use to make real decisions every day. It evaluates visual perception, domain-aware interpretation, and multi-step graphical reasoning.
Chartography Leaderboard
1
Gemini
4 Argon (High reasoning)
71.6
%
1
GPT
6 Astra (Max reasoning)
71
%
1
Claude
Opus 5.5 (Adaptive/Max)
66.3
%
1
GPT
6 Sol (Max reasoning)
53.6
%
1
Claude
Fable 5.1 (Adaptive/Max)
46.2
%
1
GPT
5.6 Sol (Max reasoning)
45
%
1
Gemini
3.8 Flash (High reasoning)
40.9
%
1
Gemini
3.7 Flash (High reasoning)
40.4
%
1
Claude
Fable 5 (Adaptive/Max)
34.8
%
1
Gemini
3.6 Flash (Medium reasoning)
34
%
1
GPT
5.6 Terra (Max reasoning)
34
%
1
Muse
Spark 1.2 (xHigh reasoning)
32.1
%
1
GPT
5.6 Luna (Max reasoning)
31.4
%
1
GPT
5.5 (xHigh reasoning)
31
%
1
GPT
5.4 (xHigh reasoning)
29.6
%
1
GPT
6 Luna (Max reasoning)
29.1
%
1
Qwen
3.8 Max (xHigh reasoning)
29.1
%
1
Muse
Spark 1.3 (xHigh reasoning)
27.6
%
1
Claude
Opus 5 (Adaptive/Max)
27.3
%
1
Kimi
K3 (Max reasoning)
26.6
%
1
Gemini
3.1 Pro (High reasoning)
26.1
%
1
Muse
Spark 1.1 (xHigh reasoning)
24.4
%
1
Grok
4.6 (xHigh reasoning)
20.5
%
1
Qwen
3.8 Flash (xHigh reasoning)
17.4
%
1
Muse
Glimmer 30B (xHigh reasoning)
17.2
%
1
Grok
4.5 (High reasoning)
17
%
1
Claude
Sonnet 5 (Adaptive/Max)
16.6
%
1
Claude
Opus 4.7 (Adaptive/Max)
16.5
%
1
GLM
5.3 Flash (Max reasoning)
16.3
%
1
Claude
Opus 4.8 (Adaptive/Max)
15.9
%
1
Qwen
3.5 Plus (Thinking on)
15.9
%
1
Qwen
3.7 Plus (Thinking on)
15.8
%
1
Grok
4.7 (xHigh reasoning)
14.7
%
1
Grok
4.3 (High reasoning)
12.9
%
1
Kimi
K2.5 (Thinking on)
12.6
%
1
Kimi
K2.6 (Thinking on)
12.2
%
1
DeepSeek
V4.1 Flash (Max reasoning)
11.6
%
1
DeepSeek
V4 Flash Vision (experimental) (Max reasoning)
11.2
%
1
Gemini
3.5 Flash-Lite (Minimal reasoning)
10.2
%
1
Inkling
Inkling (High reasoning)
10
%
1
Inkling
Small (xHigh reasoning)
9.1
%
1
Mistral
Large 3
9
%
Score vs. cost per trial
Score vs. generated tokens
VIEW ALL BENCHMARKS
Agentic Coding
sudo L7
Coding agents are getting very good at being L3s. But do they have the judgment to become L7s? Across 60 tasks, agents must navigate unfamiliar systems, choose architectures, spot hidden risks, and know when technically correct code is still the wrong thing to ship.
Rank
Model
Score
41.7
%
Claude Sonnet 5.5 (Adaptive/Max)
Anthropic
41.7
%
Claude Opus 5.5 (Adaptive/Max)
Anthropic
33.9
%
GPT 6 Astra (Max)
OpenAI
31.1
%
Claude Fable 5.1 (Adaptive/Max)
Anthropic
28.9
%
GPT 6.1 Sol (Max)
OpenAI
20.6
%
Qwen 3.8 Max
Alibaba Cloud
Agentic Finance
DAYJOB: Finance
DAYJOB: Finance measures long-horizon finance agents across corporate finance, banking, credit, investing, and real assets. It's built around the messy reality of knowledge work: realistic requests, complex environments, and end-to-end professional judgment.
Rank
Model
Score
24
%
Claude Sonnet 5.5 (Adaptive/Max)
Anthropic
23.9
%
Claude Opus 5.5 (Adaptive/Max)
Anthropic
21.5
%
GPT 6 Astra (Max)
OpenAI
21.3
%
Muse Wonder 1.0 (Max)
Meta
19.8
%
Claude Fable 5.1 (Adaptive/Max)
Anthropic
18.8
%
Gemini 4 Argon (High)
Google