Benchmarks

Zeka testi

Model quality scored 0–100 by an impartial judge LLM (Claude Sonnet 4.6, blind). Six categories: reasoning, coding, creativity, factual accuracy, instruction-following, and safety.

#1Anthropic
100
Claude Opus 4.7
Tier B
Reasoning95
Coding90
Factual100
#2Anthropic
100
Claude Sonnet 4.6
Tier A
Reasoning95
Coding90
Factual100
#3Anthropic
100
Claude Opus 4.6
Tier B
Reasoning95
Coding90
Factual100
#4Anthropic
100
Claude Opus 4.5
Tier B
Reasoning95
Coding90
Factual100
#5Anthropic
100
Claude Haiku 4.5
Tier A
Reasoning95
Coding90
Factual100
#6Anthropic
100
Claude Opus 4.1
Tier C
Reasoning95
Coding90
Factual100
#7Anthropic
100
Claude Opus 4
Tier C
Reasoning95
Coding90
Factual100
#8Anthropic
100
Claude Sonnet 4
Tier C
Reasoning95
Coding90
Factual100
#9OpenAI
100
gpt-4.1-mini-2025-04-14
Reasoning95
Coding90
Factual100
#10OpenAI
100
gpt-4.1-mini
Tier C
Reasoning95
Coding90
Factual100
#11OpenAI
100
gpt-4.1-nano-2025-04-14
Reasoning95
Coding90
Factual100
#12OpenAI
100
gpt-4.1-nano
Tier C
Reasoning95
Coding90
Factual100
#13Google Gemini
100
Gemini Flash-Lite Latest
Tier C
Reasoning95
Coding90
Factual100
#14Google Gemini
100
Nano Banana
Reasoning95
Coding90
Factual100
#15Google Gemini
100
Gemini 3 Flash Preview
Tier C
Reasoning95
Coding90
Factual100
#16Google Gemini
100
Nano Banana 2
Reasoning95
Coding90
Factual100
#17OVH AI Endpoints (GRA)
100
gpt-oss-120b
Tier C
Reasoning95
Coding90
Factual100
#18OVH AI Endpoints (GRA)
100
Mistral-Small-3.2-24B-Instruct-2506
Reasoning95
Coding90
Factual100
#19Anthropic
99
Claude Sonnet 4.5
Tier B
Reasoning94
Coding89
Factual99
#20OpenAI
99
gpt-4
Tier C
Reasoning94
Coding89
Factual99
#21OpenAI
99
gpt-4-turbo
Tier C
Reasoning94
Coding89
Factual99
#22OpenAI
99
gpt-4-turbo-2024-04-09
Tier C
Reasoning94
Coding89
Factual99
#23OpenAI
99
gpt-4o-mini
Tier C
Reasoning94
Coding89
Factual99
#24OpenAI
99
gpt-4o-2024-08-06
Tier C
Reasoning94
Coding89
Factual99
#25OpenAI
99
gpt-4o-2024-11-20
Tier C
Reasoning94
Coding89
Factual99
#26OpenAI
99
gpt-4.1-2025-04-14
Reasoning94
Coding89
Factual99
#27OpenAI
99
gpt-4.1
Tier B
Reasoning94
Coding89
Factual99
#28OpenAI
99
gpt-5-chat-latest
Tier C
Reasoning94
Coding89
Factual99
#29OpenAI
99
gpt-5-search-api
Tier C
Reasoning94
Coding89
Factual99
#30OpenAI
99
gpt-5-search-api-2025-10-14
Reasoning94
Coding89
Factual99
#31OpenAI
99
gpt-4o-search-preview-2025-03-11
Reasoning94
Coding89
Factual99
#32Google Gemini
99
Gemini 2.5 Flash-Lite
Tier B
Reasoning94
Coding89
Factual99
#33Google Gemini
99
Gemini Robotics-ER 1.6 Preview
Reasoning94
Coding89
Factual99
#34Google Gemini
99
Gemini 3.1 Flash Lite
Reasoning94
Coding89
Factual99
#35Anthropic
99
Claude Opus 4.8
Tier A
Reasoning94
Coding89
Factual99
#36OpenAI
98
gpt-3.5-turbo-16k
Reasoning93
Coding88
Factual98
#37OpenAI
98
gpt-4o
Tier C
Reasoning93
Coding88
Factual98
#38OpenAI
98
gpt-4o-2024-05-13
Tier C
Reasoning93
Coding88
Factual98
#39OpenAI
98
gpt-4o-mini-2024-07-18
Tier C
Reasoning93
Coding88
Factual98
#40OpenAI
98
gpt-4o-mini-search-preview
Tier C
Reasoning93
Coding88
Factual98
#41OpenAI
97
gpt-3.5-turbo-1106
Reasoning92
Coding87
Factual97
#42OVH AI Endpoints (GRA)
97
Llama-3.1-8B-Instruct
Reasoning92
Coding87
Factual97
#43OVH AI Endpoints (GRA)
97
Meta-Llama-3_3-70B-Instruct
Reasoning92
Coding87
Factual97
#44OVH AI Endpoints (GRA)
97
Qwen3-Coder-30B-A3B-Instruct
Reasoning92
Coding87
Factual97
#45OVH AI Endpoints (GRA)
97
Mistral-7B-Instruct-v0.3
Reasoning92
Coding87
Factual97
#46OpenAI
95
gpt-3.5-turbo
Tier C
Reasoning90
Coding86
Factual95
#47OpenAI
95
gpt-3.5-turbo-0125
Reasoning90
Coding86
Factual95
#48OpenAI
95
gpt-4o-search-preview
Tier C
Reasoning90
Coding86
Factual95
#49Google Gemini
95
Gemma 4 26B A4B IT
Tier C
Reasoning90
Coding86
Factual95
#50OVH AI Endpoints (GRA)
95
Qwen2.5-VL-72B-Instruct
Reasoning90
Coding86
Factual95
#51OVH AI Endpoints (GRA)
92
gpt-oss-20b
Tier C
Reasoning87
Coding83
Factual92
#52OpenAI
91
gpt-4-0613
Reasoning86
Coding82
Factual91
#53Google Gemini
90
Gemma 4 31B IT
Tier C
Reasoning86
Coding81
Factual90
#54Google Gemini
88
Gemini 3.5 Flash
Tier A
Reasoning84
Coding79
Factual88
#55OVH AI Endpoints (GRA)
85
Mistral-Nemo-Instruct-2407
Reasoning81
Coding77
Factual85
#56OpenAI
72
gpt-4o-mini-search-preview-2025-03-11
Reasoning68
Coding65
Factual72
#57Google Gemini
51
Gemini Pro Latest
Tier C
Reasoning48
Coding46
Factual51
#58OVH AI Endpoints (GRA)
50
Qwen3-32B
Reasoning48
Coding45
Factual50
#59Google Gemini
43
Lyria 3 Pro Preview
Reasoning41
Coding39
Factual43
#60Google Gemini
40
Gemini 3.1 Pro Preview
Tier C
Reasoning38
Coding36
Factual40
#61Google Gemini
40
Lyria 3 Clip Preview
Reasoning38
Coding36
Factual40
#62Google Gemini
35
Gemini Flash Latest
Tier B
Reasoning33
Coding32
Factual35
#63Google Gemini
35
Gemini 3.1 Pro Preview Custom Tools
Tier C
Reasoning33
Coding32
Factual35
#64Google Gemini
30
Gemini 2.5 Flash
Tier A
Reasoning29
Coding27
Factual30
#65Google Gemini
25
Nano Banana Pro
Reasoning24
Coding23
Factual25
#66Google Gemini
0
Gemini 2.5 Pro
Tier A
Reasoning0
Coding0
Factual0
#67OVH AI Endpoints (GRA)
0
Qwen3.5-9B
Reasoning0
Coding0
Factual0
#68OVH AI Endpoints (GRA)
0
Qwen3.5-397B-A17B
Reasoning0
Coding0
Factual0

68 models scored · category breakdown estimated (full per-category scoring in Q3 2026)