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 4 E4B Instruct

23 benchmarks
CompanyGoogle
Country of originUSA
WeightsOpen weights
Parameter count8.0B
Architecturegemma4
VariantReasoning
OriginInstruction tuning

Leaderboard position

#833
Overall rank (of 1126 models)
376
Elo rating
23
Benchmarks
Top 74.0%
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 23 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
AIME 2025 ~56.28 65% NVIDIA Corporation: NVIDIA Nemotron 3 Nano 4B, Technology Innovation Institute: falcon-h1r-7b, Qwen: qwen3-14b
MATH-500 ~81.85 64% NVIDIA Corporation: NVIDIA Nemotron 3 Nano 4B, Technology Innovation Institute: falcon-h1r-7b, Qwen: Qwen3 4B
IFBench ~47.05 64% Technology Innovation Institute: falcon-h1r-7b, NVIDIA Corporation: nvidia-nemotron-3.5-bolt-e4b, Meta Llama: Llama 3.3 70B Instruct
MMLU ~55.32 64% DeepSeek: DeepSeek R1, MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b
ARC-Challenge ~55.52 63% MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
ARC-Easy ~68.95 63% MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
HellaSwag ~66.29 63% MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
WinoGrande ~66.58 63% MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
Humanity's Last Exam (no tools) ~4.22 63% Technology Innovation Institute: falcon-h1r-7b, Meta Llama: Llama 3.3 70B Instruct, SpaceXAI: Grok 3
IFEval ~75.92 63% Qwen: Qwen3 4B, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
GSM8K ~70.54 63% DeepSeek: deepseek-v3, IBM Granite: granite-4.1-30b, IBM Granite: Granite 4.1 8B
SuperGPQA ~32.86 63% DeepSeek: deepseek-v3, DeepSeek: DeepSeek R1, Meta Llama: Llama 3.3 70B Instruct
TruthfulQA ~37.81 63% MWS AI: cotype-nano, LiquidAI: lfm-2.5-8b-a1b, OpenBMB: minicpm5-1b
SWE-bench Verified ~28.24 61% Qwen: Qwen3 4B, OpenAI: gpt-oss-20b, Qwen: Qwen3 8B
SciCode ~20.88 61% Technology Innovation Institute: falcon-h1r-7b, Meta Llama: Llama 3.3 70B Instruct, SpaceXAI: Grok 3
GPQA ~42.32 61% NVIDIA Corporation: NVIDIA Nemotron 3 Nano 4B, Inception: Mercury 2, NVIDIA Corporation: nvidia-nemotron-3-nano-30b-a3b
Artificial Analysis Agentic Index (Maximum Reasoning) ~6.08 61% Technology Innovation Institute: falcon-h1r-7b, DeepSeek: DeepSeek R1, Meta Llama: Llama 3.3 70B Instruct
Text Arena (Snapshot from 20 june 2026) ~1291.48 61% DeepSeek: DeepSeek R1, OpenAI: gpt-oss-20b, Inception: Mercury 2
HMMT Feb 2026 ~58.38 60% Qwen: Qwen3 4B, OpenBMB: minicpm5-1b, Qwen: Qwen3.5 35B A3B
HumanEval ~67.56 60% Qwen: Qwen3 4B, Yandex: YandexGPT Lite 5, Hugging Face Smol Models Research: smollm3-3b
AA-LCR ~36.18 60% Meta Llama: Llama 3.3 70B Instruct, SpaceXAI: Grok 3, SpaceXAI: Grok 3 Mini
MATH ~48.64 60% Mistral AI: ministral-3-14b-instruct-2512, Tencent: hy3-preview-base, Yandex: YandexGPT Lite 5
BBH ~60.63 60% Qwen: Qwen3 4B, OpenBMB: minicpm5-1b, Hugging Face Smol Models Research: smollm3-3b
MMLU-Redux ~73.11 60% Qwen: Qwen3 4B, OpenBMB: minicpm5-1b, Tencent: hy3-preview-base
MBPP ~64.96 59% Qwen: Qwen3 4B, Hugging Face Smol Models Research: smollm3-3b, Tencent: youtu-llm-2b