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

Google: Gemma 3n E4B Instruct

3 benchmarks
CompanyGoogle
Country of originUSA

Leaderboard position

#1102
Overall rank (of 1126 models)
-664
Elo rating
3
Benchmarks
Top 97.9%
Percentile
In Google (of 73 models)

Benchmark highlights

Nearest competitor from another company

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

appeared as nearest in 1 of 3 benchmarks

Benchmarks

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 ~39.48 60% Microsoft: phi-4-mini-instruct, Meta Llama: Llama 3.2 3B Instruct, LiquidAI: LFM2.5 1.2B Instruct
HellaSwag ~38.43 60% Microsoft: phi-4-mini-instruct, Qwen: Qwen3 0.6B, Meta Llama: Llama 3.2 3B Instruct
PIQA ~63.47 60% Google: Gemma 3 270M Instruct, Qwen: Qwen3.5 0.8B
WinoGrande ~51.79 60% Microsoft: phi-4-mini-instruct, Meta Llama: Llama 3.2 3B Instruct, LiquidAI: LFM2.5 1.2B Instruct
Humanity's Last Exam (no tools) ~4 60% Microsoft: phi-4-mini-instruct, Xiaomi: MiMo-V2.5 Pro
MATH-500 ~58.76 60% Microsoft: phi-4-mini-instruct, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
AIME 2025 ~16.12 60% Microsoft: phi-4-mini-instruct, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
AIME 2026 ~43.44 60% OpenBMB: minicpm5-1b, Qwen: Qwen3.5 9B
HMMT Feb 2026 ~34.88 60% OpenBMB: minicpm5-1b, Qwen: Qwen3.5 9B
GPQA Diamond ~24.35 60% Microsoft: phi-4-mini-instruct, Qwen: Qwen3.5 0.8B, OpenBMB: minicpm5-1b
MMLU-Pro ~24.95 60% Microsoft: phi-4-mini-instruct, Meta Llama: Llama 3.2 3B Instruct, Qwen: Qwen3.5 0.8B
IFEval ~60.94 60% Meta Llama: Llama 3.2 3B Instruct, LiquidAI: lfm-2.5-8b-a1b, Google: Gemma 3 270M Instruct
IFBench ~28.22 60% Microsoft: phi-4-mini-instruct, Meta Llama: Llama 3.2 3B Instruct, LiquidAI: lfm-2.5-8b-a1b
Terminal-Bench v2.1 ~8.6 60% Xiaomi: MiMo-V2.5 Pro
MMLU ~30.23 60% Microsoft: phi-4-mini-instruct, Qwen: Qwen3 0.6B, Meta Llama: Llama 3.2 3B Instruct
SWE-bench Verified ~0.5 60% Xiaomi: MiMo-V2.5 Pro
SWE-bench Pro ~5.24 60% Meta Llama: Llama 3.1 405B Instruct, Moonshot AI: Kimi K2 Instruct, Xiaomi: MiMo-V2.5 Pro
SciCode ~3.9 60% Xiaomi: MiMo-V2.5 Pro
AA-LCR ~13.18 60% Xiaomi: MiMo-V2.5 Pro
GSM8K ~28.54 60% Qwen: Qwen3 0.6B, Google: Gemma 3 270M Instruct, Meta Llama: Llama 3.1 405B Instruct
-(CoderPPL) ~-11.06 60% Microsoft: phi-4-mini-instruct, Qwen: Qwen3 0.6B, Meta Llama: Llama 3.2 3B Instruct
LiveCodeBench v6 ~21.54 60% Qwen: Qwen3.5 9B, Xiaomi: MiMo-V2.5 Pro
MATH ~3.66 60% Xiaomi: MiMo-V2.5 Pro
BBH ~30.55 60% OpenBMB: minicpm5-1b, Xiaomi: MiMo-V2.5 Pro
Artificial Analysis Intelligence Index v4.3.2 ~5 60% LiquidAI: LFM2.5 1.2B Instruct, LiquidAI: lfm-2.5-8b-a1b, Google: Gemma 3 270M Instruct