Models
Topics
Language
More

More filters

Show inactive models

Hide models that are no longer actively available on Yupp.

Turns

Filter model performance by the number of turns in a conversation.

Open license models

Filter the leaderboard to only show models that have an open license.

373
Qwen 2.5 VL 3B Instruct
613
Inception Mercury
635
Qwen 2.5 VL 72B Instruct
674
Pixtral 12B
719
Llama 3.3 70B
724
Grok 3 Mini Fast
752
OpenAI o3-mini-low
765
Magistral Medium 2509
777
OpenAI o3-mini
778
OpenAI o3-mini-high
782
Llama 4 Scout
787
Qwen3 30B A3B Thinking 2507
793
Mistral Small 3.2 24B
796
Pixtral Large
799
Grok 3 Mini

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
1288Qwen 2.5 VL 3B Instruct373±469557.7%3.0%44 tps2.5s128K$0.21$0.63
2179Inception Mercury613±255006.5%0.4%257 tps1.1s32K$0.25$1.00
3265Qwen 2.5 VL 72B Instruct635±345055.6%5.3%25 tps3.7s128K$1.01$2.79
4274Pixtral 12B674±337205.9%2.2%101 tps1.2s131K$0.08$0.08
5194Llama 3.3 70B719±185503.5%0.3%500 tps0.5s8K$0.48$0.66
6186Grok 3 Mini Fast724±151.3K4.3%1.6%44 tps0.5s131K$0.60$4.00
7175OpenAI o3-mini-low752±171.4K4.3%0.7%139 tps1.5s200K$1.10$4.40
8229Magistral Medium 2509765±186103.9%4.0%58 tps0.9s131K$2.00$5.00
9177OpenAI o3-mini777±122K3.6%0.8%143 tps3.3s200K$1.10$4.40
10214OpenAI o3-mini-high778±176303.1%2.4%231 tps10.5s200K$1.10$4.40
11160Llama 4 Scout782±151.6K4.1%0.6%88 tps5.1s131K$0.18$0.46
12148Qwen3 30B A3B Thinking 2507787±146554.4%0.5%124 tps1.2s131K$0.16$1.70
13170Mistral Small 3.2 24B793±284755.9%2.8%141 tps0.7s33K$0.02$0.08
14165Pixtral Large796±266107.6%2.5%57 tps1.3s128K$1.50$4.50
15186Grok 3 Mini799±231.9K2.6%1.2%43 tps0.5s131K$0.30$0.50
16161Qwen3 8B813±236105.4%2.4%61 tps1.4s41K$0.02$0.07
17165Qwen3 4B818±208704.9%1.9%94 tps1.5s128K$0.01$0.01
18121QwQ 32B825±161.3K5.5%5.4%41 tps2.1s16K$0.43$0.56
19126Qwen3 30B A3B832±209504.0%5.1%163 tps1.0s41K$0.06$0.21
20139GLM 4.6V837±236405.2%6.4%21 tps1.8s128K$0.38$0.90
21161Llama 4 Maverick838±102.4K4.3%1.2%88 tps2.4s1M$0.23$0.83
22133DeepSeek V3.2 Speciale842±384854.9%6.0%43 tps1.4s131K$0.84$1.52
23121Qwen3 32B Fast863±132K4.5%11.6%30 tps3.1s41K$0.10$0.25
24119ERNIE 4.5 300B A47B873±121.1K3.4%4.7%23 tps2.3s123K$0.28$1.10
25143Gemini 2.0 Flash885±168705.9%<0.1%76 tps0.5s1M$0.14$0.56
26157Qwen3 Next 80B A3B Thinking890±161.1K3.4%0.6%175 tps1.3s256K$0.21$2.26
27133GPT-4.1 nano896±111.8K3.2%0.6%175 tps0.5s1M$0.10$0.40
28157GPT-5 Nano901±91.2K5.0%3.2%113 tps20.9s400K$0.05$0.40
29143Gemini 2.0 Flash Lite902±149907.9%<0.1%42 tps0.5s1M$0.08$0.30
30133DeepSeek-R1 0528904±196404.5%1.3%93 tps0.5s64K$1.60$3.67
31124Qwen3 235B A22B Thinking 2507905±166952.1%2.5%53 tps1.6s131K$0.59$5.70
3265DeepSeek V3.2 Exp Chat909±111.3K2.6%2.6%29 tps1.5s131K$0.27$0.39
33101gpt-oss-20b912±121.5K4.1%0.5%216 tps0.5s131K$0.06$0.26
34153OpenAI o1926±159152.1%4.2%92 tps5.5s200K$15.00$60.00
35148DeepSeek-R1936±217054.1%0.8%133 tps0.6s64K$0.91$3.07
36126Qwen3 VL 235B A22B Thinking939±159653.5%4.3%47 tps3.0s127K$0.47$3.31
37133Qwen3 14B943±168254.1%1.7%109 tps0.8s41K$0.04$0.15
38139OpenAI o4-mini947±111.2K2.5%1.4%97 tps7.0s128K$1.10$4.40
39129Command A948±121.9K3.1%2.2%42 tps0.8s256K$2.00$7.33
4071Seed 1.8 251228949±181.2K2.7%3.7%41 tps2.1s256K$0.25$2.00
View All (133 models)