Preference · NVIDIA

Nemotron Nano Instruct on Arena Elo: score, rank and what it means

Nemotron Nano Instruct scores 1331.2 on Arena Elo, placing it #387 of 600 models in the index. The benchmark average is 1349.9 and the leader is Claude Opus 4.5 Max at 1501.9.

Score
1331.2
0–100 scale
Rank
#387
of 600
Percentile
36th
within the index
Benchmark avg
1349.9
all models
Leader
1501.9
Claude Opus 4.5 Max
Gap to leader
170.7
points

Score distribution

The chart shows the top 10 models on Arena Elo, with Nemotron Nano Instruct highlighted. Longer bars mean higher scores.

Claude Opus 4.5 Max 1501.9
GPT-5.2 Reasoning 1500.4
GPT-5.2 Turbo 1500.3
Claude Opus 4.5 Reasoning 1497.5
GPT-5.2 Max 1495.3
Gemini 3 Pro Turbo 1494.9
Grok 4 Max 1491.4
Claude Opus 4.5 1491.2
GPT-5.1 Pro 1490.0
Grok 4 Reasoning 1487.6

Top 10 leaderboard

#ModelProviderContextInput / 1MAvg score
1 Claude Opus 4.5 Max Anthropic 1000000 $20.90 87.8
2 GPT-5.2 Reasoning OpenAI 1000000 $20.98 87.5
3 GPT-5.2 Turbo OpenAI 1000000 $20.73 87.4
4 Claude Opus 4.5 Reasoning Anthropic 2000000 $20.91 88.2
5 GPT-5.2 Max OpenAI 1000000 $21.39 89.2
6 Gemini 3 Pro Turbo Google DeepMind 400000 $19.62 86.4
7 Grok 4 Max xAI 2000000 $19.70 86.6
8 Claude Opus 4.5 Anthropic 400000 $19.42 87.7
9 GPT-5.1 Pro OpenAI 200000 $19.77 87.8
10 Grok 4 Reasoning xAI 2000000 $19.67 87.8

What this score means

On Arena Elo, Nemotron Nano Instruct sits at #387 of 600. The leader, Claude Opus 4.5 Max, scores 1501.9, so the gap to the top is 170.7 points. The median model in this index scores 1373.8, which puts Nemotron Nano Instruct below the midpoint.

NVIDIA models average 1292.4 on this benchmark. Nemotron Nano Instruct is 38.8 points above that provider line, so it is a stronger result than the average NVIDIA model.

Among open-weight models, the average is 1338.0. Nemotron Nano Instruct is 6.8 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 1331.2 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 $2.33 per million input tokens, Nemotron Nano Instruct is below the median input price of $4.00 across the 600 models scored on Arena Elo. The models immediately around it in the ranking are shown below so you can compare score and price together.

ModelProviderContextInput / 1MAvg score
Sonar Mini Perplexity 65536 $6.52 67.9
Doubao 1.5 Pro Nano ByteDance 16384 $5.78 66.6
Claude Haiku 4.5 Nano Anthropic 8192 $6.47 68.7
Nemotron Nano Chat NVIDIA 32768 $2.21 66.2
Nemotron Nano Instruct NVIDIA 32768 $2.33 67.4
ERNIE 4.0 Mini Baidu 32768 $7.11 68.8
Molmo Allen Institute for AI 32768 $2.49 68.5

Other benchmarks for Nemotron Nano Instruct

BenchmarkScoreRankPercentileRelative
MMLU-Pro 72.6 371 38th
GPQA Diamond 64.7 366 39th
SWE-bench Verified 54.5 388 35th
HumanEval 72.9 375 38th
MATH-500 67.4 404 33th
AIME 2025 58.6 396 34th
LiveCodeBench 57.1 395 34th
IFEval 75.2 396 34th
TruthfulQA 73.0 369 39th
HellaSwag 79.7 384 36th
MMMU 66.2 368 39th

FAQ

What score does Nemotron Nano Instruct get on Arena Elo?

Nemotron Nano Instruct scores 1331.2 on Arena Elo in this index. The benchmark average is 1349.9 and the top score is 1501.9.

How does Nemotron Nano Instruct rank on Arena Elo?

It ranks #387 of 600 models, in the 36th percentile. The leader is Claude Opus 4.5 Max at 1501.9.

Is Nemotron Nano Instruct good at Arena Elo?

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 Arena Elo score calculated?

Arena Elo is a preference 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 Nemotron Nano Instruct cost?

Nemotron Nano Instruct costs $2.33 per million input tokens and $11.92 per million output tokens.

Related