Mathematics · Reka AI

Reka Core Nano on AIME 2025: score, rank and what it means

Reka Core Nano scores 57.3 on AIME 2025, placing it #404 of 600 models in the index. The benchmark average is 63.6 and the leader is Claude Opus 4.5 Pro at 91.4.

Score
57.3
0–100 scale
Rank
#404
of 600
Percentile
33th
within the index
Benchmark avg
63.6
all models
Leader
91.4
Claude Opus 4.5 Pro
Gap to leader
34.1
points

Score distribution

The chart shows the top 10 models on AIME 2025, with Reka Core Nano highlighted. Longer bars mean higher scores.

Claude Opus 4.5 Pro 91.4
GPT-5.2 Pro 91.0
GPT-5.1 Pro 90.6
GPT-5.2 90.6
o4 Reasoning 90.3
o4 Pro 89.9
Claude Opus 4.5 89.8
Gemini 3 Pro Max 89.6
Claude Opus 4.5 Max 89.3
Claude Opus 4.5 Reasoning 88.9

Top 10 leaderboard

#ModelProviderContextInput / 1MAvg score
1 Claude Opus 4.5 Pro Anthropic 200000 $20.98 89.1
2 GPT-5.2 Pro OpenAI 2000000 $21.32 89.6
3 GPT-5.1 Pro OpenAI 200000 $19.77 87.8
4 GPT-5.2 OpenAI 2000000 $19.71 88.0
5 o4 Reasoning OpenAI 1000000 $19.69 87.5
6 o4 Pro OpenAI 1000000 $19.37 87.3
7 Claude Opus 4.5 Anthropic 400000 $19.42 87.7
8 Gemini 3 Pro Max Google DeepMind 2000000 $20.57 87.9
9 Claude Opus 4.5 Max Anthropic 1000000 $20.90 87.8
10 Claude Opus 4.5 Reasoning Anthropic 2000000 $20.91 88.2

What this score means

On AIME 2025, Reka Core Nano sits at #404 of 600. The leader, Claude Opus 4.5 Pro, scores 91.4, so the gap to the top is 34.1 points. The median model in this index scores 67.6, which puts Reka Core Nano below the midpoint.

Reka AI models average 68.5 on this benchmark. Reka Core Nano is 11.2 points below that provider line, so it is a weaker result than the average Reka AI model.

Among mid-range models, the average is 60.1. Reka Core Nano is 2.8 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 57.3 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 $5.45 per million input tokens, Reka Core Nano is above the median input price of $4.00 across the 600 models scored on AIME 2025. The models immediately around it in the ranking are shown below so you can compare score and price together.

ModelProviderContextInput / 1MAvg score
Embed 4 Reasoning Cohere 4096 $5.50 65.3
ERNIE 4.5 Nano Baidu 32768 $6.01 65.6
Nova Pro Nano Amazon 8192 $5.44 65.4
Command A Nano Cohere 8192 $5.90 66.3
Reka Core Nano Reka AI 16384 $5.45 65.1
Zephyr Instruct Hugging Face 4096 $1.66 62.4
Fusion Mini OpenRouter 4096 $4.89 63.3

Other benchmarks for Reka Core Nano

BenchmarkScoreRankPercentileRelative
MMLU-Pro 68.5 412 31th
GPQA Diamond 59.9 407 32th
SWE-bench Verified 50.2 421 30th
HumanEval 68.1 413 31th
MATH-500 69.3 385 36th
LiveCodeBench 58.7 381 37th
IFEval 74.8 401 33th
TruthfulQA 67.8 416 31th
HellaSwag 79.5 390 35th
MMMU 61.8 411 32th
Arena Elo 1310.8 407 32th

FAQ

What score does Reka Core Nano get on AIME 2025?

Reka Core Nano scores 57.3 on AIME 2025 in this index. The benchmark average is 63.6 and the top score is 91.4.

How does Reka Core Nano rank on AIME 2025?

It ranks #404 of 600 models, in the 33rd percentile. The leader is Claude Opus 4.5 Pro at 91.4.

Is Reka Core Nano good at AIME 2025?

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 AIME 2025 score calculated?

AIME 2025 is a mathematics 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 Core Nano cost?

Reka Core Nano costs $5.45 per million input tokens and $25.25 per million output tokens.

Related