Toolathlon

Name: Toolathlon — AI Model Benchmark Results
Creator: Neura Market

Multi-tool orchestration — using multiple tools to solve complex tasks.

agent0-100 percent

Model Rankings (30)

#	Model	Score	Provider	Source
1	M Muse Spark 1.1🇺🇸	75.6	Meta	verified
2	M Kimi K3🇨🇳	73.2	Moonshot AI	verified
3	Claude Opus 4.8🇺🇸	59.9	Anthropic	verified
4	GPT-5.6 Sol🇺🇸	58	OpenAI	verified
5	Gemini 3.5 Flash🇺🇸	56.5	Google	verified
6	GPT-5.5🇺🇸	55.6	OpenAI	verified
7	GPT-5.4🇺🇸	54.6	OpenAI	verified
8	Claude Sonnet 5🇺🇸	54.3	Anthropic	verified
9	GPT-5.6 Luna🇺🇸	53.4	OpenAI	verified
10	GPT-5.6 Terra🇺🇸	53.1	OpenAI	verified
11	DeepSeek-V4-Pro-Max🇨🇳	51.8	DeepSeek	verified
12	B Seed 2.1 Pro🇨🇳	50.6	ByteDance	verified
13	M Kimi K2.6🇨🇳	50	Moonshot AI	verified
14	Gemini 3 Flash🇺🇸	49.4	Google	verified
15	B Seed 2.1 Turbo🇨🇳	49.1	ByteDance	verified
16	T Hy3🇨🇳	48.5	Tencent	verified
17	Z GLM-5.2🇨🇳	48.2	Zhipu AI	verified
18	DeepSeek-V4-Flash-Max🇨🇳	47.8	DeepSeek	verified
19	MiniMax M2.7🇨🇳	46.3	MiniMax	verified
20	GPT-5.2🇺🇸	46.3	OpenAI	verified
21	MiniMax M2.1🇨🇳	43.5	MiniMax	verified
22	GPT-5.4 mini🇺🇸	42.9	OpenAI	verified
23	Z GLM-5.1🇨🇳	40.7	Zhipu AI	verified
24	Q Qwen3.6 Plus🇨🇳	39.8	Alibaba Cloud / Qwen Team	verified
25	Q Qwen3.5-397B-A17B🇨🇳	38.3	Alibaba Cloud / Qwen Team	verified
26	GPT-5.4 nano🇺🇸	35.5	OpenAI	verified
27	DeepSeek-V3.2 (Thinking)🇨🇳	35.2	DeepSeek	verified
28	DeepSeek-V3.2🇨🇳	35.2	DeepSeek	verified
29	DeepSeek-V3.2-Speciale🇨🇳	35.2	DeepSeek	verified
30	Q Qwen3.6-35B-A3B🇨🇳	26.9	Alibaba Cloud / Qwen Team	verified