Skip to content

Benchmark

Workspace-Bench · English Full · Atria run

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.13

Score distribution

61%
Mean
63.9%
Median
3.9%
Std dev
56%
10th percentile
65.8%
90th percentile
55.7%
Min
55.7%65.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.13 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 5Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.8%
2GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
3Qwen3.8 MaxAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
4Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.6%
5GPT-5.6 SolAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56%
6DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.7%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.