BrowseComp

BrowseComp - web browsing and comprehension agentic benchmark.

Category

General Agents

Max Score

100.0

Score Type

percent

Active

Yes

Model Scores

Scores for BrowseComp

Model Score Date Verified
GLM 5.1 Thinking
86.49%
11.06.2026 Unverified
GPT 5.5
92.28%
11.06.2026 Unverified
GLM-5.1
63.90%
04.06.2026 Unverified
Kimi K2.6
66.06%
04.06.2026 Unverified
Qwen3.5-397B-A17B
42.45%
04.06.2026 Unverified
DeepSeek-V4-Pro
63.90%
04.06.2026 Unverified
DeepSeek-V4-Flash
79.57%
26.06.2026 Verified
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
46.88%
04.06.2026 Verified
MiniMax-M2.7
57.89%
04.06.2026 Unverified
DeepSeek V4 Pro
91.15%
11.06.2026 Unverified
Claude Sonnet 4.6
81.27%
11.06.2026 Unverified
Claude Opus 4.7
86.49%
11.06.2026 Unverified
MiniMax-M3
91.26%
11.06.2026 Unverified
Gemini 3.1 Pro
93.98%
11.06.2026 Unverified
Kimi K3
100.00%
18.08.2026 Verified
Qwen3.5-122B-A10B
68.90%
01.02.2026 Verified
Qwen3.5-27B
65.72%
01.02.2026 Unverified
Qwen3.5-35B-A3B
65.72%
01.02.2026 Unverified
GPT-5-mini 2025-08-07
51.08%
01.02.2026 Unverified
Ornith-1.5-35B-A3B
73.21%
19.08.2026 Verified
Ornith-1.0-35B-A3B
68.56%
19.08.2026 Unverified
Qwen3.6-35B-A3B
66.86%
19.08.2026 Unverified
GPT-5.4
90.35%
23.08.2026 Verified
Claude Opus 4.6
91.49%
23.08.2026 Verified
Kimi K2.5
81.50%
23.08.2026 Verified
Opus-4.6
91.49%
26.06.2026 Verified
DeepSeek-V4-Pro
87.74%
26.06.2026 Verified
Spark-X2.5-4B
42.91%
— Verified
Spark-X2.5-1.7B
30.19%
— Verified
Qwen3.5-9B
5.90%
— Verified
Qwen3.5-4B
12.71%
— Verified
Qwen3.5-2B
3.10
— Verified
Gemma4-12B
7.83%
— Verified
Gemma4-E4B
5.90%
— Verified
Gemma4-E2B
0.68%
— Verified
MiniCPM5-2B
41.54%
— Verified
LFM2.5-2.6B
12.03%
— Verified
granite-4.2-3B
18.05%
— Verified
Nemotron-3-Nano-4B
1.82%
— Verified
LFM2.5-8B-A1B
7.49%
— Verified