Skip to content

Benchmark

WideSearch item F1

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
40
Sources
2
IQ weight
0.00

Score distribution

72.9%
Mean
74.4%
Median
6.6%
Std dev
65.8%
10th percentile
80.8%
90th percentile
59.4%
Min
59.4%84%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, perplexity, server-tool, 25, high· OpenRouter benchmark exports84%
2GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, perplexity, server-tool, 25, xhigh· OpenRouter benchmark exports83.4%
3GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, native, server-tool, 25, high· OpenRouter benchmark exports81.8%
4GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, perplexity, server-tool, 5, high· OpenRouter benchmark exports81.4%
5Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · hide-tool-result context management· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.8%
6GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, parallel, server-tool, 25, high· OpenRouter benchmark exports80.6%
7GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, perplexity, server-tool, 5, xhigh· OpenRouter benchmark exports80%
8GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, perplexity, server-tool, 1, high· OpenRouter benchmark exports79.8%
9Kimi K2.5Agent Swarm· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.79%
10GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, native, server-tool, 5, high· OpenRouter benchmark exports78.4%
11GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, exa, server-tool, 25, xhigh· OpenRouter benchmark exports78%
12GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, parallel, server-tool, 5, high· OpenRouter benchmark exports77.8%
13GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, parallel, server-tool, 1, high· OpenRouter benchmark exports77.4%
14GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, exa, server-tool, 25, high· OpenRouter benchmark exports77.4%
15DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, perplexity, server-tool, 25, high· OpenRouter benchmark exports77.1%
16GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, native, server-tool, 1, high· OpenRouter benchmark exports76.9%
17GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, exa, server-tool, 5, xhigh· OpenRouter benchmark exports75.7%
18DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, exa, server-tool, 25, high· OpenRouter benchmark exports74.5%
19GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, parallel, server-tool, 25, xhigh· OpenRouter benchmark exports74.4%
20GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, exa, server-tool, 5, high· OpenRouter benchmark exports74.4%
21GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, parallel, server-tool, 5, xhigh· OpenRouter benchmark exports72.9%
22Kimi K2.5single agent· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.7%
23DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, perplexity, server-tool, 5, high· OpenRouter benchmark exports72.1%
24DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, parallel, server-tool, 25, high· OpenRouter benchmark exports71.2%
25GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, perplexity, server-tool, 1, xhigh· OpenRouter benchmark exports71.1%
26GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, exa, server-tool, 1, xhigh· OpenRouter benchmark exports69.1%
27Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, perplexity, server-tool, 25, high· OpenRouter benchmark exports68.2%
28GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, exa, server-tool, 1, high· OpenRouter benchmark exports68.2%
29GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, parallel, server-tool, 1, xhigh· OpenRouter benchmark exports67.9%
30Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, perplexity, server-tool, 5, high· OpenRouter benchmark exports67.8%
31Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, exa, server-tool, 25, high· OpenRouter benchmark exports67%
32DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, exa, server-tool, 5, high· OpenRouter benchmark exports66.3%
33DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, parallel, server-tool, 5, high· OpenRouter benchmark exports66.2%
34Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, parallel, server-tool, 25, high· OpenRouter benchmark exports65.9%
35Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, perplexity, server-tool, 1, high· OpenRouter benchmark exports65.8%
36Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, exa, server-tool, 5, high· OpenRouter benchmark exports65.8%
37Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, parallel, server-tool, 5, high· OpenRouter benchmark exports65.2%
38Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, parallel, server-tool, 1, high· OpenRouter benchmark exports61.7%
39Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, exa, server-tool, 1, high· OpenRouter benchmark exports59.6%
40DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, parallel, server-tool, 1, high· OpenRouter benchmark exports59.4%

Data credits: OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · 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.