AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Benchmarks

BrowseComp

OpenAI's benchmark for evaluating AI agents on complex web browsing and information retrieval tasks that require multi-step reasoning over live web content.

agenticbenchmark_matrix

Strengths

Tests real-world information retrieval requiring browsing, reasoning, and synthesis across web pages.

Caveats

Requires agentic capabilities (browsing). Models without tool use score zero.

How to interpret scores

Contamination risk: moderateFreshness: static

Higher is better. Accuracy percentage on retrieval tasks (0–100%).

Caveat to keep in mind

Requires agentic capabilities (browsing).

Leaderboard

Last synced: Nov 22, 2026, 12:18 PM
#ModelProviderScorePrice/M
1
Gemma 3 270M
source benchpress
Evidence observed Apr 13, 2026
Google99.5$0.00
2
Qwen3.5 0.8B (Reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba99.2$0.00
3
Llama 2 Chat 7B
source benchpress
Evidence observed Apr 13, 2026
Meta98.7$0.00
4
Meta: Llama 3.2 1B Instruct
source benchpress
Evidence observed Apr 13, 2026
Meta93.9$0.07
5
Granite 4.0 350M
source benchpress
Evidence observed Apr 13, 2026
IBM93.7$0.00
6
Gemma 3 1B Instruct
source benchpress
Evidence observed Apr 13, 2026
Google93.5$0.00
7
AlfredPros: CodeLLaMa 7B Instruct Solidity
source benchpress
Evidence observed Apr 13, 2026
Alfredpros91.9$0.90
8
LFM2.5-1.2B-Instruct
source benchpress
Evidence observed Apr 13, 2026
Liquid AI91.6$0.00
9
Mistral: Ministral 3 3B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI91.4$0.10
10
Qwen3.5 0.8B (Non-reasoning)
source benchpress
Evidence observed Apr 13, 2026
Alibaba91.3$0.00
11
Llama 3.2 Instruct 1B
source benchpress
Evidence observed Apr 13, 2026
Meta91.0$0.00
12
LFM2 1.2B
source benchpress
Evidence observed Apr 13, 2026
Liquid AI90.8$0.00
13
Llama 2 Chat 70B
source benchpress
Evidence observed Apr 13, 2026
Meta90.7$0.00
14
Mistral 7B Instruct
source benchpress
Evidence observed Apr 13, 2026
Mistral AI90.2$0.16
15
Mistral: Ministral 3 8B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI89.9$0.15
16
Ministral 3 3B
source benchpress
Evidence observed Apr 13, 2026
Mistral AI89.8$0.10
17
LFM2.5-VL-1.6B
source benchpress
Evidence observed Apr 13, 2026
Liquid AI89.5$0.00
18
Qwen: Qwen VL Max
source benchpress
Evidence observed Apr 13, 2026
Alibaba89.4$1.40
19
GPT-5.4 Pro (Xhigh)
source benchmark_matrix
Evidence observed Apr 16, 2026
OpenAI89.3$67.50
20
DeepSeek R1 Distill Qwen 1.5B
source benchpress
Evidence observed Apr 13, 2026
DeepSeek89.2$0.00
21
Granite 4.0 H 350M
source benchpress
Evidence observed Apr 13, 2026
IBM89.2$0.00
22
Reka Edge
source benchpress
Evidence observed Apr 13, 2026
Reka88.7$0.20
23
Reka Edge
source benchpress
Evidence observed Apr 13, 2026
Rekaai88.7$0.10
24
Mistral: Ministral 3 14B 2512
source benchpress
Evidence observed Apr 13, 2026
Mistral AI88.1$0.20
25
Apertus 8B Instruct
source benchpress
Evidence observed Apr 13, 2026
Swiss AI Initiative87.8$0.00
26
Cohere: Command R7B (12-2024)
source benchpress
Evidence observed Apr 13, 2026
Cohere87.8$0.07
27
Claude Instant
source benchpress
Evidence observed Apr 13, 2026
Anthropic87.7$0.00
28
Cohere: Command R+ (08-2024)
source benchpress
Evidence observed Apr 13, 2026
Cohere87.5$4.38
29
Cohere: Command R (08-2024)
source benchpress
Evidence observed Apr 13, 2026
Cohere87.5$0.26
30
Apertus 70B Instruct
source benchpress
Evidence observed Apr 13, 2026
Swiss AI Initiative87.4$0.00
31
OLMo 2 7B
source benchpress
Evidence observed Apr 13, 2026
Allen Institute for AI87.3$0.00
32
Claude Mythos Preview
source benchmark_matrix
Evidence observed Apr 16, 2026
Anthropic86.9—
33
Gemini 3 Deep Think
source benchpress
Evidence observed Apr 13, 2026
Google86.9$0.00
34
DeepSeek R1 Distill Llama 8B
source benchpress
Evidence observed Apr 13, 2026
DeepSeek86.8$0.00
35
Gemini 1.5 Pro (May '24)
source benchpress
Evidence observed Apr 13, 2026
Google86.7$0.00
36
TNG: DeepSeek R1T2 Chimera (free)
source benchpress
Evidence observed Apr 13, 2026
Tngtech86.6$0.00
37
Gemini 3.1 Pro Preview
source benchmark_matrix
Evidence observed Feb 25, 2026
Google85.9$4.50
38
Google: Gemini 3.1 Pro Preview Custom Tools
source benchmark_matrix
Evidence observed Feb 26, 2026
Google85.9$4.50
39
Gemini 3 Pro Preview (High)
source benchmark_matrix
Evidence observed Feb 26, 2026
Google85.9$4.50
40
Granite 4.0 H 1B
source benchpress
Evidence observed Apr 13, 2026
IBM85.6$0.00
41
LFM2 24B A2B
source benchpress
Evidence observed Apr 13, 2026
Liquid AI85.3$0.00
42
Granite 4.0 1B
source benchpress
Evidence observed Apr 13, 2026
IBM85.2$0.00
43
Meta: Llama 3.2 3B Instruct (free)
source benchpress
Evidence observed Apr 13, 2026
Meta85.2$0.00
44
Meta: Llama 3.2 3B Instruct
source benchpress
Evidence observed Apr 13, 2026
Meta85.2$0.02
45
Tiny Aya Global
source benchpress
Evidence observed Apr 13, 2026
Cohere84.9$0.00
46
LFM2.5-1.2B-Thinking
source benchpress
Evidence observed Apr 13, 2026
Liquid AI84.8$0.00
47
OpenChat 3.5 (1210)
source benchpress
Evidence observed Apr 13, 2026
OpenChat84.8$0.00
48
Nanbeige4.1-3B
source benchpress
Evidence observed Apr 13, 2026
Nanbeige84.6$0.00
49
Mistral: Mistral 7B Instruct v0.3
source benchpress
Evidence observed Apr 13, 2026
Mistral AI84.5$0.20
50
Mistral: Mistral 7B Instruct v0.1
source benchpress
Evidence observed Apr 13, 2026
Mistral AI84.5$0.13