gpt.college

Artificial Analysis · Checked 2026-10-02

Overall Ranking

Equal-weight average of five normalized capability indices: coding, reasoning, research, multimodal and agentic.

All rankings
Method Equal-weight average of five normalized capability indices: coding, reasoning, research, multimodal and agentic.

Overall is the mean of five normalized 0–100 capability indices; it is calculated by gpt.college. All five scores are required.

Rank Model Provider Overall (0–100) State Coding (%)Reasoning (%)Research (Elo)Multimodal (%)Agentic (%)
1
Claude Opus 5.5
Equal-weight mean · five normalized capability indices
 Anthropic 93.5 Calculated ↗ 60%61%184626%70%
2
Claude Sonnet 5.5
Equal-weight mean · five normalized capability indices
 Anthropic 93 Calculated ↗ 64%55%184426%71%
3
GPT-6 Astra
Equal-weight mean · five normalized capability indices
 OpenAI 90.6 Calculated ↗ 59%55%154231%68%
4
GPT-6.1 Sol
Equal-weight mean · five normalized capability indices
 OpenAI 88.6 Calculated ↗ 56%53%157531%65%
5
Gemini 4 Argon
Equal-weight mean · five normalized capability indices
 Google 88.2 Calculated ↗ 57%57%161122%78%
6
Claude Fable 5.1
Equal-weight mean · five normalized capability indices
 Anthropic 86.3 Calculated ↗ 52%59%173526%59%
7
GPT-6 Sol
Equal-weight mean · five normalized capability indices
 OpenAI 77.8 Calculated ↗ 44%48%150525%62%
8
Qwen3.8-Max-0902
Equal-weight mean · five normalized capability indices
 Alibaba Cloud 73.6 Calculated ↗ 39%43%167223%56%
9
Grok 4.7
Equal-weight mean · five normalized capability indices
 xAI 70.4 Calculated ↗ 26%43%169520%66%
10
GLM-5.3
Equal-weight mean · five normalized capability indices
 Z.ai 67.8 Calculated ↗ 42%42%165611%62%
11
GLM-5.3-Flash
Equal-weight mean · five normalized capability indices
 Z.ai 66.3 Calculated ↗ 33%40%164515%60%
12
Gemini 3.8 Flash
Equal-weight mean · five normalized capability indices
 Google 66.2 Calculated ↗ 20%48%141221%60%
12
Grok 4.6
Equal-weight mean · five normalized capability indices
 xAI 66.2 Calculated ↗ 21%43%160917%67%
14
Kimi K3
Equal-weight mean · five normalized capability indices
 Moonshot AI 65.2 Calculated ↗ 13%47%154022%58%
15
DeepSeek-V4.1-Flash
Equal-weight mean · five normalized capability indices
 DeepSeek 64.6 Calculated ↗ 27%39%160013%69%
16
Qwen3.8-Max
Equal-weight mean · five normalized capability indices
 Alibaba Cloud 62.9 Calculated ↗ 19%43%160820%49%
17
GPT-6 Luna
Equal-weight mean · five normalized capability indices
 OpenAI 60.8 Calculated ↗ 13%39%143823%53%
18
MiniMax M3
Equal-weight mean · five normalized capability indices
 MiniMax 38.7 Calculated ↗ 2%39%124610%21%
19
Mistral Medium 3.5
Equal-weight mean · five normalized capability indices
 Mistral 16.2 Calculated ↗ 0%14%7473%6%

Other catalog models

No score for this exact benchmark in the selected snapshot. Available historical results remain in each profile.

27 other models

Outside this benchmark snapshot

Qwen3.8-Flash-Next

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Sonnet 5

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Haiku 4.5

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Mythos 5.1

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3.8 Flash Cyber

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

GPT-5.6 Sol

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

GPT-5.6 Terra

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

GPT-5.6 Luna

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3.5 Flash

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3.6 Flash

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Fable 5

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Opus 5

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Opus 4.8

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Opus 4.7

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

DeepSeek V4 Pro

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

DeepSeek V4 Flash

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

OpenAI GPT-5.4

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Claude Opus 4.6

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3.1 Pro

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3 Pro

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

DeepSeek-R1

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Gemini 3.7 Flash

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Qwen3.8-Flash

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

DeepSeek-V3

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Tencent Hunyuan-Large

—

No score is inferred or assigned a ranking position.

Outside this benchmark snapshot

Hunyuan-T1

—

No score is inferred or assigned a ranking position.

Missing evidence is not zero. Higher reasoning effort may cost more, and small margins in rounded scores need not be significant. Full methodology →