Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
EQ-Bench 3 Benchmark Leaderboard | Phaseo
EQ-Bench 3
EQ-Bench 3
AI benchmark results and model performance
Summary
â–¼
Summary
â–¼
Type: numerical
View benchmark source
Recorded Results
34
Average Score
1103
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
OpenAI
GPT 4 (2023-03-14)
14 Mar 2023
435
-
No
Source
Mistral
Mistral Small 3.1
17 Mar 2025
638
-
No
Source
Qwen
Qwen 2.5 72B
-
692
-
No
Source
Qwen
Qwen 3 30B A3B
-
730
-
No
Source
Google
Gemini 2.0 Flash
05 Feb 2025
775
-
No
Source
OpenAI
GPT OSS 20b
05 Aug 2025
800
-
No
Source
Google
Gemma 3 4B
12 Mar 2025
856
-
No
Source
OpenAI
GPT 4.1 Nano
14 Apr 2025
904
-
No
Source
Qwen
Qwen 3 32B
-
953
-
No
Source
SpaceXAI
Grok 3 Mini Beta
19 Feb 2025
985
-
No
Source
Google
Gemma 3 27B
12 Mar 2025
1041
-
No
Source
SpaceXAI
Grok 3 Beta
19 Feb 2025
1066
-
No
Source
Anthropic
Claude 3.5 Sonnet (2024-10-22)
22 Oct 2024
1068
-
No
Source
Anthropic
Claude 3.7 Sonnet
24 Feb 2025
1083
-
No
Source
OpenAI
GPT 4.5 Preview
27 Feb 2025
1093
-
No
Source
Mistral
Mistral Small 3.2
20 Jun 2025
1127
-
No
Source
OpenAI
GPT 4.1 Mini
14 Apr 2025
1145
-
No
Source
OpenAI
GPT OSS 120b
05 Aug 2025
1152
-
No
Source
DeepSeek
DeepSeek V3 (2025-03-24)
24 Mar 2025
1170
-
No
Source
SpaceXAI
Grok 4
10 Jul 2025
1193
-
No
Source
Qwen
QwQ 32B
-
1214
-
No
Source
OpenAI
GPT 4.1
14 Apr 2025
1235
-
No
Source
Google
Gemini 2.5 Pro Preview (2025-05-06)
06 May 2025
1247
-
No
Source
Anthropic
Claude Sonnet 4
21 May 2025
1261
-
No
Source
DeepSeek
DeepSeek R1 (2025-01-20)
20 Jan 2025
1270
-
No
Source
Qwen
Qwen 3 235B A22B
-
1275
-
No
Source
OpenAI
o4 Mini
16 Apr 2025
1291
-
No
Source
Anthropic
Claude Opus 4
21 May 2025
1296
-
No
Source
z.AI
GLM 4.5
28 Jul 2025
1312
-
No
Source
OpenAI
GPT 5 Chat
07 Aug 2025
1357
-
No
Source
Google
Gemini 2.5 Pro Preview (2025-06-05)
05 Jun 2025
1470
-
No
Source
OpenAI
o3
16 Apr 2025
1500
-
No
Source
Moonshot
Kimi K2 (2025-09-05)
05 Sept 2025
1563
-
No
Source
Score Range
435 - 1563
Leading Model (lowest score)
435 - GPT 4 (2023-03-14)