Skip to content

Benchmark

CL-bench Life · Communication & Social Interactions

Scores are percentages. Higher is better.

Models and systems measured
22
Scores recorded
46
Sources
2
IQ weight
1.92

Score distribution

9.6%
Mean
10.4%
Median
8.2%
Std dev
0.126%
10th percentile
21.5%
90th percentile
0.086%
Min
0.086%23.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.92 for chat models, measured over 14 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
1GPT 5.5high· Epoch AI Benchmarking Hub data23.5%
2GPT 5.5benchmark-owner leaderboard run · site model-mode label: GPT 5.5 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±0.7 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs23.5%
3GPT 5.4benchmark-owner leaderboard run · site model-mode label: GPT 5.4 (xHigh) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs23%
4GPT 5.4xhigh· Epoch AI Benchmarking Hub data23%
5GPT 5.4benchmark-owner leaderboard run · site model-mode label: GPT 5.4 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±0.7 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs22.2%
6GPT 5.4high· Epoch AI Benchmarking Hub data22.2%
7Claude Opus 4.6benchmark-owner leaderboard run · site model-mode label: Claude Opus 4.6 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±3.3 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs21.7%
8Claude Opus 4.6high· Epoch AI Benchmarking Hub data21.7%
9Gemini 3.1 Pro Previewbenchmark-owner leaderboard run · site model-mode label: Gemini 3.1 Pro · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs21.5%
10GPT 5.1high· Epoch AI Benchmarking Hub data21.5%
11Claude Opus 4.6· Epoch AI Benchmarking Hub data20.7%
12Claude Opus 4.6benchmark-owner leaderboard run · site model-mode label: Claude Opus 4.6 · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs20.7%
13Gemini 3.1 Pro Preview· Epoch AI Benchmarking Hub data18.8%
14Gemini 3.1 Pro Previewbenchmark-owner leaderboard run · site model-mode label: Gemini 3.1 Pro (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±1.7 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs18.8%
15GPT 5.4· Epoch AI Benchmarking Hub data17%
16GPT 5.4benchmark-owner leaderboard run · site model-mode label: GPT 5.4 · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs17%
17Kimi K2.5· Epoch AI Benchmarking Hub data15.3%
18Kimi K2.5benchmark-owner leaderboard run · site model-mode label: Kimi K2.5 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±1.1 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs15.3%
19Qwen3.5 Plus· Epoch AI Benchmarking Hub data13.1%
20Grok 4.20· Epoch AI Benchmarking Hub data12.8%
21DeepSeek V4 Prohigh· Epoch AI Benchmarking Hub data12.6%
22GLM 4.7· Epoch AI Benchmarking Hub data12.6%
23DeepSeek V3.2benchmark-owner leaderboard run · site model-mode label: DeepSeek V3.2 Thinking · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±1.1 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs12.3%
24DeepSeek V3.2 Expthinking· Epoch AI Benchmarking Hub data12.3%
25DeepSeek V3.2· Epoch AI Benchmarking Hub data10.4%
26DeepSeek V3.2benchmark-owner leaderboard run · site model-mode label: DeepSeek V3.2 · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs10.4%
27Kimi K2.5benchmark-owner leaderboard run · site model-mode label: Kimi K2.5 · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs10.4%
28MiMo V2 Pro· Epoch AI Benchmarking Hub data9.6%
29MiMo V2 Probenchmark-owner leaderboard run · site model-mode label: MiMo v2 Pro (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs9.6%
30MiniMax M2.5· Epoch AI Benchmarking Hub data8.6%
31MiniMax M2.5benchmark-owner leaderboard run · site model-mode label: MiniMax M2.5 (Thinking) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±2.1 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs8.6%

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
DeepSeek V4 Pro (CL-bench label)benchmark-owner leaderboard run · site model-mode label: DeepSeek V4 Pro (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±1.6 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs12.6%
GLM-4.7 (CL-bench label)benchmark-owner leaderboard run · site model-mode label: GLM-4.7 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs12.6%
GPT-5.1 (CL-bench label)benchmark-owner leaderboard run · site model-mode label: GPT 5.1 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs21.5%
Grok 4.20benchmark-owner leaderboard run · site model-mode label: Grok 4.20 · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs9.6%
Grok 4.20benchmark-owner leaderboard run · site model-mode label: Grok 4.20 (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±0.9 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs12.8%
Hy2.0 (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Hy2.0 Thinking · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±1.5 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.9.4%
Hy3 Preview (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Hy3 preview (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±2.1 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.17%
Hy3 Preview (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Hy3 preview (Low) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.18.5%
Hy3 Preview (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Hy3 preview (NoThink) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.13.3%
Qwen3.5 Plusbenchmark-owner leaderboard run · site model-mode label: Qwen 3.5 Plus · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs11.1%
Qwen3.5 Plusbenchmark-owner leaderboard run · site model-mode label: Qwen 3.5 Plus (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±0.9 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs13.1%
Seed 2.0 Pro (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Seed 2.0 Pro · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs8.1%
Seed 2.0 Pro (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Seed 2.0 Pro (High) · 405 tasks · GPT-5.1 judge · high reasoning effort · site standard deviation ±2.3 percentage points · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs19.8%
Seed 2.0 Pro (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Seed 2.0 Pro (Low) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs13.3%
Seed 2.0 Pro (CL-bench label)benchmark-owner leaderboard run · site model-mode label: Seed 2.0 Pro (Medium) · 405 tasks · GPT-5.1 judge · high reasoning effort · single run; no standard deviation · candidate API snapshot and exact candidate harness not specified on public leaderboard· Reported by Tencent Hunyuan / Fudan NLP Group· via BenchBoard docs11.9%

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. · Epoch AI Benchmarking Hub, CC BY 4.0 (licence)