Skip to content

Benchmark

GraphWalks Parents

Scores are percentages. Higher is better.

Models measured
11
Scores recorded
30
Sources
1
IQ weight
0.95

Score distribution

86.9%
Mean
93.6%
Median
16.6%
Std dev
62%
10th percentile
99.3%
90th percentile
32.4%
Min
32.4%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.95 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1MiMo V2.5official model-card chart · accuracy · 128K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.100%
2MiMo V2.5official model-card chart · accuracy · 32K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.100%
3MiMo V2.5official model-card chart · accuracy · 64K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.100%
4Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · 256K · accuracy· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.3%
5Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · 256K · accuracy· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.3%
6MiMo V2.5 Proofficial model-card chart · accuracy · 128K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99%
7MiMo V2.5official model-card chart · accuracy · 256K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98%
8MiMo V2.5 Proofficial model-card chart · accuracy · 32K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98%
9MiMo V2.5 Proofficial model-card chart · accuracy · 64K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98%
10Claude Sonnet 4.6256K API-reproducible subset of 1M · F1 · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.97.9%
11MiMo V2.5official model-card chart · accuracy · 512K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.97%
12MiMo V2.5 Proofficial model-card chart · accuracy · 256K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.97%
13Claude Sonnet 4.6256K API-reproducible subset of 1M · F1 · 64K extended thinking· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.9%
14Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · 256K · accuracy· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.6%
15Claude Opus 4.7public-API-reproducible 256K subset · accuracy · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.6%
16MiMo V2.5 Proofficial model-card chart · accuracy · 512K input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92%
17GPT 5.5256K · F1 · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.1%
18GPT 5.5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · 256K · accuracy· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.1%
19GPT 5.5Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted · 256K · accuracy· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.1%
20GPT 5.40K-128K · accuracy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.8%
21GPT 5.2<128K · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89%
22GPT 5.20K-128K · accuracy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89%
23MiMo V2.5official model-card chart · accuracy · 1M input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87%
24Claude Opus 4.7256K–1M aggregate · accuracy · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.1%
25Claude Opus 4.6Anthropic Opus 4.6 launch page · adaptive thinking · max effort unless noted · 1M · Parents · F1· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72%
26GPT-5.4 minixhigh · 0K–128K · accuracy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.5%
27MiMo V2.5 Proofficial model-card chart · accuracy · 1M input tokens· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62%
28GPT 5.51M · F1 · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.5%
29GPT 5.4 Nanoxhigh · 0K–128K · accuracy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.8%
30GPT 5.4256K-1M · accuracy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.32.4%

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.