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

cloudflare: clef-flash

6 benchmarks
Companycloudflare

Leaderboard position

#593
Overall rank (of 1121 models)
882
Elo rating
6
Benchmarks
Top 52.9%
Percentile
In cloudflare (of 3 models)

Benchmark highlights

Best benchmark
MMLU 91.8

Nearest competitor from another company

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

appeared as nearest in 1 of 6 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
MATH-500 ~86.81 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
AIME 2025 ~65.99 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
Humanity's Last Exam (no tools) ~12.13 60% Xiaomi: MiMo-V2.5 Pro, Microsoft: phi-4-mini-instruct
IFEval ~82.45 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
HumanEval ~74.86 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
MBPP ~78.05 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
Terminal-Bench v2.1 ~22.46 60% recursiveai: ripple-65b-preview, Xiaomi: MiMo-V2.5 Pro
SWE-bench Verified ~40.06 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, recursiveai: ripple-65b-preview
SWE-bench Pro ~18.94 60% recursiveai: ripple-65b-preview, Xiaomi: MiMo-V2.5 Pro
SciCode ~27.35 60% recursiveai: ripple-65b-preview, Xiaomi: MiMo-V2.5 Pro
AA-LCR ~43.64 60% recursiveai: ripple-65b-preview, Xiaomi: MiMo-V2.5 Pro
GSM8K ~83.15 60% Qwen: qwen3-1.7b, Yandex: gpt-5-lite-pretrain, Sber: gigachat3.5-432b-a28b-base
-(CoderPPL) ~-1.69 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Hugging Face Smol Models Research: smollm3-3b
LiveCodeBench v6 ~55.74 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Qwen: qwen3-1.7b
MATH ~61.92 60% Mistral AI: mistral-small-3.2-24b-instruct-2506, Yandex: gpt-5-lite-pretrain, Moonshot AI: Moonlight Instruct
ARC-Challenge ~69.82 60% Sber: gigachat3.5-432b-a28b-base, Technology Innovation Institute: falcon-h1-1.5b-deep-instruct, Xiaomi: MiMo-V2.5 Pro
HellaSwag ~81.34 60% Sber: gigachat3.5-432b-a28b-base, Technology Innovation Institute: falcon-h1-1.5b-deep-instruct, Xiaomi: MiMo-V2.5 Pro
PIQA ~84.39 60% Arcee AI: trinity-nano-base, Technology Innovation Institute: falcon3-mamba-7b-base, Qwen: Qwen3.5 0.8B
CowQA ~69.68 60% Tencent: youtu-llm-2b, Qwen: Qwen3 4B, Google: Gemma 3 4B Instruct
GPQA ~49.26 60% Mistral AI: mistral-small-3.2-24b-instruct-2506, Technology Innovation Institute: falcon-h1-1.5b-deep-instruct, Xiaomi: MiMo-V2.5 Pro
ParseBench ~44.45 60% Qwen: Qwen3.5 9B, Qwen: Qwen3.5 0.8B
Artificial Analysis Intelligence Index v4.1.1 (Maximum Reasoning) ~15.43 60% Xiaomi: MiMo-V2.5 Pro
Terminal-Bench v2.0 ~19.56 60% Xiaomi: MiMo-V2.5 Pro
ScreenSpot-Pro ~53.76 60% Qwen: Qwen3.5 9B, Qwen: Qwen3.5 0.8B
Artificial Analysis Intelligence Index v4.1 (Maximum Reasoning) ~16.52 60% Qwen: Qwen3 4B, Qwen: qwen3-1.7b, Xiaomi: MiMo-V2.5 Pro