Model comparison
Mercury 2.5 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 16× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
NVIDIASummary
- They share 3 benchmarks with published results for both. Mercury 2.5 scores higher in 1 category and Nemotron 3 Ultra in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Ultra leads 35.3 to 23.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 260K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Inception | NVIDIA |
| Noometry Index | 33.5 | 42.5 |
| Released | 2026-09-08 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 260K | 262K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.04 | $0.60 |
| Output $ / M tokens | $0.15 | $2.40 |
| Results tracked | 4 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
Mercury 2.5: 39.5 (#156), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 38.5% | 40.3% |
| FrontierCode | — | 13.6% |
| WeirdML | — | 43.5% |
| LMArena Coding | — | 1468 |
| ALE-Bench | 301.65 | — |
Agentic & Tool Use Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Mercury 2.5: 22.4 (#193), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Nemotron 3 Ultra leads
Mercury 2.5: 23.3 (#272), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 3% | 2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LMArena Math | — | 1457 |
Knowledge Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
Multilingual Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |
Long Context Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Not comparable
Mercury 2.5: —, Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Mercury 2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is Mercury 2.5 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 16× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Mercury 2.5 or Nemotron 3 Ultra?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Mercury 2.5 or Nemotron 3 Ultra better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 260K.
How many benchmarks do Mercury 2.5 and Nemotron 3 Ultra share?
3 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Nemotron 3 Ultra has 30.