Claude Opus 4 vs Nemotron 3 Super 120B A12B
Wins 2 of 4 areas
Coding · Long documents
Wins 1 of 4 areas
Reasoning
Claude Opus 4 wins more areas, narrowly.Nemotron 3 Super 120B A12B is cheaper and better at reasoning.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the four areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Long documents rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Nemotron 3 Super 120B A12B costs 99% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 4 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+18.8points ahead
- Code for real scientific research problemsSciCode+3.6points ahead
- Reasons across sets of long documentsAA-LCR+3.6points ahead
Where Nemotron 3 Super 120B A12B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8.5points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4
- SWE-bench VerifiedClaude Opus 4 by 18.872.553.7+18.8
- SciCodeClaude Opus 4 by 3.639.836.2+3.6
- Terminal-Bench HardClaude Opus 4 by 2.331.128.8+2.3
ReasoningNemotron 3 Super 120B A12B
- Humanity's Last ExamNemotron 3 Super 120B A12B by 8.512.320.8+8.5
- GPQA Diamondtie79.680tie
Following instructionsEven
- IFBenchNemotron 3 Super 120B A12B by 17.853.771.5+17.8
- Multi-ChallengeClaude Opus 4 by 3.458.655.2+3.4
Other results11 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- HMMT 2025Nemotron 3 Super 120B A12B by 78.815.994.7+78.8
- τ²-Bench (Retail)Claude Opus 4 by 1981.862.8+19
- Terminal-BenchClaude Opus 4 by 17.443.225.8+17.4
- AIME 2025Nemotron 3 Super 120B A12B by 14.775.590.2+14.7
- LiveCodeBenchNemotron 3 Super 120B A12B by 10.870.481.2+10.8
- AA IntelligenceClaude Opus 4 by 7.820.612.8+7.8
- MMLUClaude Opus 4 by 6.992.986+6.9
- τ²-Bench Telecom (AA run)Claude Opus 4 by 5.673.467.8+5.6
- Artificial Analysis Coding IndexNemotron 3 Super 120B A12B by 3.73437.7+3.7
- Tau2 airlineClaude Opus 4 by 3.76056.3+3.7
- MMLU-ProClaude Opus 4 by 2.986.683.7+2.9
Questions people ask
Which is better, Claude Opus 4 or Nemotron 3 Super 120B A12B?
Claude Opus 4 wins two of the four areas where both have results: coding and long documents. Nemotron 3 Super 120B A12B wins reasoning, and costs 99% less. They are level on following instructions.
Which is better for coding?
Claude Opus 4. It wins 3 of the 3 coding tests both models report; Nemotron 3 Super 120B A12B wins none.
Which is cheaper?
Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens; Nemotron 3 Super 120B A12B costs $0.30 and $0.90. That makes Nemotron 3 Super 120B A12B about 99% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.