Commonsense · Reka AI

Reka Flash Mini on HellaSwag: score, rank and what it means

Reka Flash Mini scores 77.9 on HellaSwag, placing it #404 of 600 models in the index. The benchmark average is 81.4 and the leader is GPT-5.2 Max at 96.1.

Score
77.9
0–100 scale
Rank
#404
of 600
Percentile
33th
within the index
Benchmark avg
81.4
all models
Leader
96.1
GPT-5.2 Max
Gap to leader
18.2
points

Score distribution

The chart shows the top 10 models on HellaSwag, with Reka Flash Mini highlighted. Longer bars mean higher scores.

GPT-5.2 Max 96.1
GPT-5.2 Turbo 95.5
GPT-5.2 Pro 95.3
Claude Opus 4.5 Pro 95.2
Claude Sonnet 4.5 Reasoning 95.2
Grok 4 Reasoning 95.2
GPT-5.2 Vision 94.6
Gemini 3 Pro Turbo 94.6
GPT-5.1 Reasoning 94.4
o4 Pro 94.4

Top 10 leaderboard

#ModelProviderContextInput / 1MAvg score
1 GPT-5.2 Max OpenAI 1000000 $21.39 89.2
2 GPT-5.2 Turbo OpenAI 1000000 $20.73 87.4
3 GPT-5.2 Pro OpenAI 2000000 $21.32 89.6
4 Claude Opus 4.5 Pro Anthropic 200000 $20.98 89.1
5 Claude Sonnet 4.5 Reasoning Anthropic 400000 $19.48 87.7
6 Grok 4 Reasoning xAI 2000000 $19.67 87.8
7 GPT-5.2 Vision OpenAI 1000000 $19.03 87.4
8 Gemini 3 Pro Turbo Google DeepMind 400000 $19.62 86.4
9 GPT-5.1 Reasoning OpenAI 400000 $20.27 88.3
10 o4 Pro OpenAI 1000000 $19.37 87.3

What this score means

On HellaSwag, Reka Flash Mini sits at #404 of 600. The leader, GPT-5.2 Max, scores 96.1, so the gap to the top is 18.2 points. The median model in this index scores 83.6, which puts Reka Flash Mini below the midpoint.

Reka AI models average 83.8 on this benchmark. Reka Flash Mini is 5.9 points below that provider line, so it is a weaker result than the average Reka AI model.

Among mid-range models, the average is 79.8. Reka Flash Mini is 1.9 points below that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.

Read a 77.9 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.

Price context

At $5.77 per million input tokens, Reka Flash Mini is above the median input price of $4.00 across the 600 models scored on HellaSwag. The models immediately around it in the ranking are shown below so you can compare score and price together.

ModelProviderContextInput / 1MAvg score
Kimi K2 7B Moonshot AI 16384 $1.72 62.7
Molmo Chat Allen Institute for AI 32768 $2.40 66.7
Nemotron Nano NVIDIA 8192 $2.24 66.6
DeepSeek-R1 8B DeepSeek 16384 $1.87 64.3
Reka Flash Mini Reka AI 16384 $5.77 65.5
SmolLM3 Hugging Face 8192 $1.71 63.1
Molmo Base Allen Institute for AI 4096 $2.02 65.0

Other benchmarks for Reka Flash Mini

BenchmarkScoreRankPercentileRelative
MMLU-Pro 68.1 417 31th
GPQA Diamond 60.2 404 33th
SWE-bench Verified 50.7 416 31th
HumanEval 71.2 386 36th
MATH-500 67.0 408 32th
AIME 2025 59.4 391 35th
LiveCodeBench 58.2 387 36th
IFEval 73.9 407 32th
TruthfulQA 72.0 380 37th
MMMU 61.6 415 31th
Arena Elo 1313.6 402 33th

FAQ

What score does Reka Flash Mini get on HellaSwag?

Reka Flash Mini scores 77.9 on HellaSwag in this index. The benchmark average is 81.4 and the top score is 96.1.

How does Reka Flash Mini rank on HellaSwag?

It ranks #404 of 600 models, in the 33rd percentile. The leader is GPT-5.2 Max at 96.1.

Is Reka Flash Mini good at HellaSwag?

It is below the median for this benchmark, so test it carefully before relying on it for this capability. The result should be read alongside its price and context window.

How is the HellaSwag score calculated?

HellaSwag is a commonsense benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.

What does Reka Flash Mini cost?

Reka Flash Mini costs $5.77 per million input tokens and $27.64 per million output tokens.

Related