Skip to content

Benchmark

JobBench

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models and systems measured
27
Scores recorded
40
Sources
2
IQ weight
1.75

Score distribution

53.4%
Mean
54.7%
Median
13.1%
Std dev
33.4%
10th percentile
65.7%
90th percentile
15.9%
Min
15.9%75.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.75 for chat models, measured over 26 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.3%
2Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.5%
3Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.5%
4Claude Opus 5Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68%
5Claude Opus 5max · 65 tasks · official evaluation code · OpenCode · file-aware rubric grader · mean rubric score· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.7%
6LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.4%
7Muse Spark 1.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.9%
8Muse Spark 1.3max · 65 tasks · official evaluation code · OpenCode · file-aware rubric grader · mean rubric score· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.9%
9MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62%
10Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.8%
11Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.7%
12Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.7%
13Muse Spark 1.2xhigh · 65 tasks · official evaluation code · OpenCode · file-aware rubric grader · mean rubric score· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.6%
14MiMo V2.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.2%
15GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.2%
16Claude Fable 5Qwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.4%
17Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.7%
18Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.7%
19Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.7%
20Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.7%
21Muse Spark 1.1Meta Model API · xhigh · OpenCode · Grok 4.3 judge · official JobBench results· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.7%
22Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.3%
23Kimi K3max effort · temp 1.0 · top_p 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.3%
24DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.1%
25Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.4%
26Qwen3.8 MaxQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.4%
27Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.9%
28Qwen3.8 MaxAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.7%
29Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.6%
30Claude Opus 4.8max · OpenCode · Grok 4.3 judge · official JobBench results· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.4%
31Claude Opus 4.8Qwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.4%
32GPT-5.6 SolAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.4%
33GPT-5.6 Solmax · 65 tasks · official evaluation code · OpenCode · file-aware rubric grader · mean rubric score· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.4%
34GPT-5.6 SolQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.4%
35GPT 5.5xhigh · OpenCode · Grok 4.3 judge · official JobBench results· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.38.3%
36Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.4%
37Qwen 3.8 27BQwen3.8-27B model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.33.4%
38Qwen3.7 MaxQwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31.3%
39Gemini 3.1 Pro Previewhigh · OpenCode · Grok 4.3 judge · official JobBench results· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.15.9%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · OpenCode · Grok 4.3 judge · official JobBench results· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.17%

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. · Data by LLM Stats