Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

appvoid: arco-3

5 benchmarks
Companyappvoid
Country of originDominican Republic

Leaderboard position

#1016
Overall rank (of 1121 models)
-157
Elo rating
5
Benchmarks
Top 90.6%
Percentile
#1
In appvoid (of 2 models)
Above: Sapbot: Gemma 4 31B Instruct Distill Qwen3 0.6B LoRA #1015 Below: Yandex: gpt-3-lite #1017

Benchmark highlights

Best benchmark
PIQA 68.17
Worst benchmark
ARC-Challenge 36.01

Nearest competitor from another company

The model from another company with the most similar benchmark scores.

appeared as nearest in 1 of 5 benchmarks

LiquidAI: lfm-2-350m
1/5 20.0%
LiquidAI: LFM2.5 1.2B Instruct
1/5 20.0%
Mistral AI: devstral-small-2505
1/5 20.0%
Hugging Face Smol Models Research: smollm2-135m
1/5 20.0%
Apple: openelm-450m
1/5 20.0%
Model Votes % of benchmarks
LiquidAI: lfm-2-350m 1 20.0%
LiquidAI: LFM2.5 1.2B Instruct 1 20.0%
Mistral AI: devstral-small-2505 1 20.0%
Hugging Face Smol Models Research: smollm2-135m 1 20.0%
Apple: openelm-450m 1 20.0%

Benchmarks

PIQA 68.17 WinoGrande 58.09 HellaSwag 49.56 MMLU 43.34 ARC-Challenge 36.01

Predicted scores

Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.

Benchmark Predicted Confidence Based on
ARC-Easy ~52.79 62% LiquidAI: LFM2.5 1.2B Instruct, Apple: openelm-450m, Apple: openelm-270m
MMLU-Pro ~36.23 61% OpenBMB: minicpm5-1b, Qwen: Qwen3.5 0.8B, Google: gemma-3-1b-pt
IFEval ~68.06 61% OpenBMB: minicpm5-1b, Hugging Face Smol Models Research: smollm2-135m-instruct, Qwen: Qwen3.5 0.8B
IFBench ~36.52 61% OpenBMB: minicpm5-1b, Qwen: Qwen3.5 0.8B, LiquidAI: lfm-2.5-8b-a1b
GSM8K ~41.96 61% Hugging Face Smol Models Research: smollm2-135m-instruct, Qwen: Qwen3 0.6B, Hugging Face Smol Models Research: smollm2-135m
-(CoderPPL) ~-6.78 61% LiquidAI: LFM2.5 1.2B Instruct, OpenBMB: minicpm5-1b, Qwen: Qwen3 0.6B
BBH ~42.98 61% OpenBMB: minicpm5-1b, Hugging Face Smol Models Research: smollm2-135m-instruct, Google: gemma-3-1b-pt
CowQA ~35.4 61% LiquidAI: LFM2.5 1.2B Instruct, Qwen: Qwen3 0.6B, LiquidAI: lfm-2.5-8b-a1b
Artificial Analysis Intelligence Index v4.1 (Maximum Reasoning) ~1 61% LiquidAI: LFM2.5 1.2B Instruct, Mistral AI: devstral-small-2505, OpenBMB: minicpm5-1b
Artificial Analysis Intelligence Index v4.0 (Maximum Reasoning) ~7.2 61% LiquidAI: LFM2.5 1.2B Instruct, OpenBMB: minicpm5-1b, Qwen: Qwen3 0.6B
WikiText-2 (-ppl) ~-65.67 61% LiquidAI: LFM2.5 1.2B Instruct, Mistral AI: devstral-small-2505, OpenBMB: minicpm5-1b
TruthfulQA ~29.87 61% LiquidAI: LFM2.5 1.2B Instruct, Apple: openelm-270m, Mistral AI: devstral-small-2505
GPQA Diamond ~35.12 60% OpenBMB: minicpm5-1b, Qwen: Qwen3.5 0.8B, LiquidAI: LFM2.5-230M
HumanEval ~45.06 60% Qwen: qwen-1.8b, Technology Innovation Institute: falcon-h1-1.5b-instruct, Hugging Face Smol Models Research: smollm3-3b
MBPP ~39.38 60% Google: gemma-3-1b-pt, Qwen: qwen-1.8b, Technology Innovation Institute: falcon-h1-1.5b-instruct
Terminal-Bench v2.1 ~8.6 60% Xiaomi: MiMo-V2.5 Pro
SWE-bench Pro ~5.24 60% Xiaomi: MiMo-V2.5 Pro
SciCode ~11.12 60% Xiaomi: MiMo-V2.5 Pro
AA-LCR ~23.34 60% Xiaomi: MiMo-V2.5 Pro
Artificial Analysis Intelligence Index v4.3.2 ~5 60% LiquidAI: LFM2.5 1.2B Instruct, OpenBMB: minicpm5-1b, Qwen: Qwen3.5 0.8B
BrowseComp ~13.26 60% NON AI - НЕ ИИ: Random baseline - Случайный счёт, NON AI - НЕ ИИ: Human baseline - Человеческий результат
GPQA ~20.29 60% Qwen: Qwen3.5 0.8B, Google: gemma-3-1b-pt, Technology Innovation Institute: falcon-h1-1.5b-instruct
Artificial Analysis Intelligence Index v4.1.1 (Maximum Reasoning) ~3 60% Xiaomi: MiMo-V2.5 Pro
Terminal-Bench v2.0 ~0 60% NON AI - НЕ ИИ: Random baseline - Случайный счёт, Xiaomi: MiMo-V2.5 Pro, NON AI - НЕ ИИ: Human baseline - Человеческий результат
Artificial Analysis Agentic Index (Maximum Reasoning) ~3.8 60% Qwen: Qwen3 0.6B, Xiaomi: MiMo-V2.5 Pro