Codesota · Benchmark · Polish EQ-BenchHome/Leaderboards/Polish EQ-Bench
Unknown

Polish EQ-Bench.

Evaluates LLMs on emotional intelligence in Polish. Based on EQ-Bench v2 methodology adapted for Polish language. Models predict emotional intensity changes across 171 questions. Score adjusted for parseability: Benchmark Score × (Parseable / 171). Created by SpeakLeash.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Eq Score

Eq Score is the reported evaluation metric for Polish EQ-Bench. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Eq Scoreverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01mistralai/Mistral-Large-Instruct-2407verified78.072026Source ↗Looks wrong?
02mistralai/Mistral-Large-Instruct-2411verified77.292026Source ↗Looks wrong?
03Meta-Llama-3.1-405B-Instruct-FP8verified77.232026Source ↗Looks wrong?
04GPT-4o-2024-08-06verified75.152026Source ↗Looks wrong?
05gpt-4-turbo-2024-04-09verified74.5864332026Source ↗Looks wrong?
06speakleash/Bielik-11B-v2.6-Instructverified73.6964912026Source ↗Looks wrong?
07deepseek-ai/DeepSeek-V3-0324 (API)verified73.462026Source ↗Looks wrong?
08Mistral-Small-Instruct-2409verified72.852026Source ↗Looks wrong?
09CYFRAGOVPL/Llama-PLLuM-70B-chatverified72.5631582026Source ↗Looks wrong?
10meta-llama/Meta-Llama-3.1-70B-Instructverified72.532026Source ↗Looks wrong?
11speakleash/Bielik-11B-v2.5-Instructverified71.9964912026Source ↗Looks wrong?
12Qwen/Qwen2-72B-Instructverified71.2270762026Source ↗Looks wrong?
13meta-llama/Meta-Llama-3-70B-Instructverified71.212026Source ↗Looks wrong?
14speakleash/Bielik-11B-v3.0-Instructverified71.22026Source ↗Looks wrong?
15GPT-4o-mini-2024-07-18verified71.152026Source ↗Looks wrong?
16Qwen/Qwen2.5-32B-Instructverified71.152026Source ↗Looks wrong?
17speakleash/Bielik-11B-v2.3-Instructverified70.862026Source ↗Looks wrong?
18meta-llama/Llama-3.3-70B-Instructverified70.7295912026Source ↗Looks wrong?
19mistralai/Mistral-Small-24B-Instruct-2501verified70.522026Source ↗Looks wrong?
20CYFRAGOVPL/Llama-PLLuM-70B-instructverified69.992026Source ↗Looks wrong?
21alpindale/WizardLM-2-8x22B (API)verified69.562026Source ↗Looks wrong?
22Qwen/Qwen2.5-14B-Instructverified69.1730992026Source ↗Looks wrong?
23speakleash/Bielik-11B-v2.2-Instructverified69.052026Source ↗Looks wrong?
24Qwen2-72Bverified68.9342112026Source ↗Looks wrong?
25Qwen/Qwen2.5-72B-Instructverified68.4871352026Source ↗Looks wrong?
26speakleash/Bielik-11B-v2.0-Instructverified68.242026Source ↗Looks wrong?
27Qwen/Qwen1.5-72B-Chatverified68.032026Source ↗Looks wrong?
28mistralai/Mixtral-8x22B-Instruct-v0.1 (API)verified67.632026Source ↗Looks wrong?
29THUDM/glm-4-9b-chatverified61.792026Source ↗Looks wrong?
30mistralai/Mistral-Nemo-Instruct-2407verified61.762026Source ↗Looks wrong?
31speakleash/Bielik-11B-v2.1-Instructverified60.0692982026Source ↗Looks wrong?
32Qwen1.5-32B-Chatverified59.6252632026Source ↗Looks wrong?
33openchat/openchat-3.5-0106-gemmaverified59.5795322026Source ↗Looks wrong?
34microsoft/phi-4verified59.0999422026Source ↗Looks wrong?
35Qwen/Qwen2.5-7B-Instructverified58.582026Source ↗Looks wrong?
36aya-23-35Bverified58.412026Source ↗Looks wrong?
37GPT-3.5-turboverified57.72026Source ↗Looks wrong?
38Qwen2-57B-A14B-Instructverified57.642026Source ↗Looks wrong?
39mistralai/Mixtral-8x7B-Instruct-v0.1verified57.6112282026Source ↗Looks wrong?
40c4ai-command-r-v01verified56.432026Source ↗Looks wrong?
41Phi-3-medium-4k-instructverified56.4025152026Source ↗Looks wrong?
42upstage/SOLAR-10.7B-Instruct-v1.0verified55.2133332026Source ↗Looks wrong?
43CYFRAGOVPL/pllum-12b-nc-chat-250715verified55.1652632026Source ↗Looks wrong?
44Hermes-2-Theta-Llama-3-8Bverified54.882026Source ↗Looks wrong?
45NeuralDaredevil-8B-abliteratedverified54.742026Source ↗Looks wrong?
46Hermes-2-Pro-Llama-3-8Bverified54.572026Source ↗Looks wrong?
47utter-project/EuroLLM-9B-Instructverified54.1096492026Source ↗Looks wrong?
48Qwen1.5-32Bverified54.0321642026Source ↗Looks wrong?
49Qwen2-7B-Instructverified53.742026Source ↗Looks wrong?
50speakleash/Bielik-4.5B-v3.0-Instructverified53.5802922026Source ↗Looks wrong?
51recurrentgemma-9b-itverified52.822026Source ↗Looks wrong?
52CYFRAGOVPL/PLLuM-12B-chatverified52.2645612026Source ↗Looks wrong?
53Qwen1.5-72Bverified51.4355562026Source ↗Looks wrong?
54microsoft/Phi-4-mini-instructverified50.5228072026Source ↗Looks wrong?
55berkeley-nest/Starling-LM-7B-alphaverified49.632026Source ↗Looks wrong?
56Nous-Hermes-2-SOLAR-10.7Bverified49.2669592026Source ↗Looks wrong?
57openchat-3.5-1210verified49.042026Source ↗Looks wrong?
58Delexa-7bverified48.456552026Source ↗Looks wrong?
59Qwen1.5-14B-Chatverified47.9625732026Source ↗Looks wrong?
60CYFRAGOVPL/PLLuM-8x7B-nc-chatverified47.292026Source ↗Looks wrong?
61Mistral-7B-Instruct-v0.2verified47.021932026Source ↗Looks wrong?
62meta-llama/Meta-Llama-3-8B-Instructverified46.532026Source ↗Looks wrong?
63Yi-1.5-9B-Chatverified46.4978952026Source ↗Looks wrong?
6401-ai/Yi-1.5-34B-Chatverified46.322026Source ↗Looks wrong?
65CYFRAGOVPL/Llama-PLLuM-8B-chatverified46.2008772026Source ↗Looks wrong?
66meta-llama/Llama-3.2-3B-Instructverified46.1883042026Source ↗Looks wrong?
67aya-23-8Bverified45.432026Source ↗Looks wrong?
68openchat/openchat-3.5-0106verified45.4228072026Source ↗Looks wrong?
69nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16verified45.2840942026Source ↗Looks wrong?
70CYFRAGOVPL/PLLuM-8x7B-chatverified45.222026Source ↗Looks wrong?
71mistralai/Mistral-7B-Instruct-v0.3verified45.212026Source ↗Looks wrong?
72Kruk-7B-SP-001verified44.442026Source ↗Looks wrong?
73Starling-LM-7B-betaverified43.7812872026Source ↗Looks wrong?
74OpenChat3.5-0106-Spichlerz-Bocianverified42.8396492026Source ↗Looks wrong?
75falcon-11Bverified42.412026Source ↗Looks wrong?
76CYFRAGOVPL/PLLuM-8x7B-nc-instructverified41.752026Source ↗Looks wrong?
77OpenChat3.5-0106-Spichlerz-Inst-001verified41.62026Source ↗Looks wrong?
78internlm2-chat-7b-sftverified41.3766082026Source ↗Looks wrong?
79CYFRAGOVPL/PLLuM-8x7B-instructverified39.552026Source ↗Looks wrong?
80internlm2-chat-7bverified39.5321642026Source ↗Looks wrong?
81Llama3-ChatQA-1.5-8Bverified39.3643272026Source ↗Looks wrong?
82Meta-Llama-3-70Bverified39.0906432026Source ↗Looks wrong?
83OpenHermes-2.5-Mistral-7Bverified37.482026Source ↗Looks wrong?
84internlm/internlm2-chat-20bverified36.3064332026Source ↗Looks wrong?
85CYFRAGOVPL/PLLuM-12B-instructverified36.2125152026Source ↗Looks wrong?
86Qwen/Qwen2.5-3B-Instructverified35.8690062026Source ↗Looks wrong?
87Qwen2-7Bverified35.5104092026Source ↗Looks wrong?
88OpenHermes-13Bverified34.9105262026Source ↗Looks wrong?
89Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1verified34.1714622026Source ↗Looks wrong?
90speakleash/Bielik-7B-Instruct-v0.1verified31.263862026Source ↗Looks wrong?
91Qwen/Qwen2.5-1.5B-Instructverified27.6274852026Source ↗Looks wrong?
92Llama-3-8B-Omnibus-1-PL-v01-INSTRUCTverified26.632026Source ↗Looks wrong?
93Phi-3-mini-4k-instructverified26.0815792026Source ↗Looks wrong?
94Voicelab/trurl-2-13b-academicverified24.5557892026Source ↗Looks wrong?
95Qwen1.5-7B-Chatverified23.9766082026Source ↗Looks wrong?
96Qwen1.5-7Bverified20.9476612026Source ↗Looks wrong?
97meta-llama/Llama-3.2-1B-Instructverified17.8205852026Source ↗Looks wrong?
98gemma-1.1-2b-itverified16.472026Source ↗Looks wrong?
99Qwen2-1.5B-Instructverified14.7921052026Source ↗Looks wrong?
100internlm2-chat-1_8bverified12.1315792026Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards
Polish EQ-Bench Leaderboard | CodeSOTA | CodeSOTA