Commonsense · Reka AI

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

Reka Flash Pro scores 86.1 on HellaSwag, placing it #216 of 600 models in the index. The benchmark average is 81.4 and the leader is GPT-5.2 Max at 96.1.

Score
86.1
0–100 scale
Rank
#216
of 600
Percentile
64th
within the index
Benchmark avg
81.4
all models
Leader
96.1
GPT-5.2 Max
Gap to leader
10.0
points

Score distribution

The chart shows the top 10 models on HellaSwag, with Reka Flash Pro 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 Pro sits at #216 of 600. The leader, GPT-5.2 Max, scores 96.1, so the gap to the top is 10.0 points. The median model in this index scores 83.6, which puts Reka Flash Pro above the midpoint.

Reka AI models average 83.8 on this benchmark. Reka Flash Pro is 2.3 points above that provider line, so it is a stronger result than the average Reka AI model.

Among multimodal models, the average is 86.8. Reka Flash Pro is 0.7 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 86.1 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 $10.82 per million input tokens, Reka Flash Pro 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
Llama 3 DeepInfra Instruct DeepInfra 65536 $3.84 75.5
Magistral Chat Mistral AI 128000 $4.33 76.8
Nemotron 4 NVIDIA 65536 $4.18 76.6
Nova Pro Turbo Amazon 128000 $13.18 78.4
Reka Flash Pro Reka AI 200000 $10.82 75.2
Sonar Perplexity 200000 $10.57 76.0
Llama 3 Anyscale Anyscale 65536 $3.94 74.7

Other benchmarks for Reka Flash Pro

BenchmarkScoreRankPercentileRelative
MMLU-Pro 76.3 298 50th
GPQA Diamond 71.2 236 61th
SWE-bench Verified 61.8 287 52th
HumanEval 78.6 278 54th
MATH-500 79.2 229 62th
AIME 2025 68.4 289 52th
LiveCodeBench 69.6 201 67th
IFEval 82.8 251 58th
TruthfulQA 77.8 260 57th
MMMU 75.0 164 73th
Arena Elo 1396.5 218 64th

FAQ

What score does Reka Flash Pro get on HellaSwag?

Reka Flash Pro scores 86.1 on HellaSwag in this index. The benchmark average is 81.4 and the top score is 96.1.

How does Reka Flash Pro rank on HellaSwag?

It ranks #216 of 600 models, in the 64th percentile. The leader is GPT-5.2 Max at 96.1.

Is Reka Flash Pro good at HellaSwag?

Yes, relative to the index: it is above the median and inside the top half of scores. 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 Pro cost?

Reka Flash Pro costs $10.82 per million input tokens and $52.20 per million output tokens.

Related