TECHAGENT - MY AI LIFE

AI Model Benchmarks

Standard: 36 · HF: 22

About these benchmarks

Benchmarks are standardised tests that score how well AI models handle reasoning, knowledge, math and coding. Use them to compare models objectively and pick the right one for your task.

📊 Standard. Standard - the four most-cited public benchmarks (MMLU, GPQA, HumanEval, SWE-Bench), taken from each model's announcement page; our Score weights them into a single number.

🤗 HF Open LLM Leaderboard. HF Open LLM Leaderboard - six tasks (IFEval, BBH, MATH, GPQA, MuSR, MMLU-Pro) measured uniformly for open-source models; ranked by the Average.

📊 Standard (MMLU · GPQA · HumanEval · SWE-Bench)🤗 HF Open LLM Leaderboard
📚MMLU
57 academic subjects
o1
OpenAI
92.3%
🔬GPQA Diamond
PhD-level science questions
o1
OpenAI
77.3%
💻HumanEval
Python code generation
DeepSeek R1
DeepSeek
92.6%
🔧SWE-Bench
Real GitHub engineering tasks
Claude Opus 4.1
Anthropic
74.5%
📚MMLU

57 academic subjects

🔬GPQA Diamond

PhD-level science questions

💻HumanEval

Python code generation

🔧SWE-Bench

Real GitHub engineering tasks

AllOpen SourceAnthropic (4)OpenAI (4)Google (4)Yandex (3)Meta (3)
#Model↕Provider↕MMLU↕GPQA↕HumanEval↕SWE-Bench↕Score↑
1MetaLlama 3.2 3BMeta
63.4
24.7
58.3
9.5
37.0
2Mistral AIMistral NeMoMistral AI
68.0
32.0
73.4
15.0
45.3
3CohereCommand R+Cohere
80.4
30.1
74.2
16.8
47.9
4GoogleGemma 2 27BGoogle
75.2
38.4
74.0
14.7
48.7
5GoogleGemini 1.5 FlashGoogle
78.9
37.0
78.9
16.2
50.7
6OpenAIGPT-4o miniOpenAI
82.0
40.1
87.1
22.8
55.9
7MetaLlama 3.1 70BMeta
83.6
46.7
80.5
21.8
56.3
8GoogleGemini 2.0 FlashGoogle
83.0
45.0
85.0
22.0
56.9
9GoogleGemini 1.5 ProGoogle
85.9
46.2
84.1
26.9
58.8
10Alibaba/QwenQwen 2.5 Coder 32BAlibaba/Qwen
80.0
42.0
92.3
30.0
59.2
11Alibaba/QwenQwen 2.5 72BAlibaba/Qwen
86.1
49.0
86.5
23.7
59.5
12AnthropicClaude Haiku 4.5Anthropic
82.9
43.0
88.3
33.2
59.9
13Mistral AIMistral Large 2Mistral AI
84.0
47.2
92.1
32.6
62.1
14SberGigaChat ProSber
68.0
-
60.0
-63.6
15MetaLlama 3.1 405BMeta
88.6
50.7
89.0
34.1
63.7
16YandexYandexGPT 4 LiteYandex
69.0
-
62.0
-65.1
17HyperCLOVA XNaver
79.0
-
55.0
-65.7
18OpenAIGPT-4oOpenAI
88.7
53.6
90.2
38.3
65.9
19AlibabaQwen MaxAlibaba
89.0
59.0
87.0
37.0
66.5
20YandexYandexGPT 3 ProYandex
72.0
-
65.0
-68.1
21DeepSeekDeepSeek V3DeepSeek
88.5
59.1
89.4
42.0
68.3
22SberGigaChat MaxSber
74.0
-
68.0
-70.7
23BaiduERNIE 4.5Baidu
88.0
55.0
82.0
-72.8
24OpenAIo3-miniOpenAI
86.9
67.4
91.7
49.3
72.9
25MiniMax Text-01MiniMax
88.0
56.0
84.0
-73.9
26AnthropicClaude Sonnet 4.6Anthropic
88.3
65.0
92.0
57.0
74.4
27YandexYandexGPT 4 ProYandex
78.0
-
72.0
-74.7
28DeepSeekDeepSeek R1DeepSeek
90.8
71.5
92.6
49.2
75.1
29OpenAIo1OpenAI
92.3
77.3
92.4
48.9
77.0
30TencentHunyuan ProTencent
81.0
-
74.0
-77.1
31ByteDanceDoubao Pro 32KByteDance
82.0
-
75.0
-78.1
32BaiduERNIE 4.0 TurboBaidu
82.0
-
76.0
-78.7
33Zhipu AIGLM-4 PlusZhipu AI
83.0
-
76.0
-79.1
34Moonshot AIMoonshot v1 128KMoonshot AI
83.0
-
77.0
-79.7
35AnthropicClaude Opus 4.7Anthropic
90.1
74.3
92.1
72.5
81.5
36AnthropicClaude Opus 4.1Anthropic---
74.5
-
Score = MMLU×20% + GPQA×30% + HumanEval×25% + SWE-Bench×25%All scores in % · higher is better→ Full model table with pricing & speed