Model comparison
Mercury 2 vs Nova Premier 1.0
Mercury 2 is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in instruction following, where Mercury 2 leads 70.4 to 66.9.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 128K.
Side by side
| Mercury 2 | Nova Premier 1.0 | |
|---|---|---|
| Provider | Inception | Amazon |
| Noometry Index | 38.8 | 37.7 |
| Released | 2026-02-20 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 50K | 10K |
| Input $ / M tokens | $0.25 | $2.50 |
| Output $ / M tokens | $0.75 | $12.50 |
| Results tracked | 17 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mercury 2: 33.2 (#250), Nova Premier 1.0: —
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| LMArena Coding | 1391 | — |
| ALE-Bench | 785.58 | — |
Reasoning Too close to call
Mercury 2: 23.0 (#170), Nova Premier 1.0: 22.3 (#182)
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| CritPt | 0.8% | — |
| LMArena Hard Prompts | 1362 | — |
Math Not comparable
Mercury 2: —, Nova Premier 1.0: 31.5 (#194)
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
Knowledge Too close to call
Mercury 2: 35.6 (#170), Nova Premier 1.0: 35.4 (#176)
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| Vectara Hallucination Rate | 12.3% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1358 | — |
Multilingual Not comparable
Mercury 2: 46.8 (#153), Nova Premier 1.0: —
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |
Instruction Following Mercury 2 leads
Mercury 2: 70.4 (#161), Nova Premier 1.0: 66.9 (#201)
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
Mercury 2: 40.4 (#149), Nova Premier 1.0: —
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1329 | — |
Writing & Preference Mercury 2 leads
Mercury 2: 54.0 (#151), Nova Premier 1.0: 51.0 (#174)
| Benchmark | Mercury 2 | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1358 | — |
Frequently asked questions
Is Mercury 2 better than Nova Premier 1.0?
Mercury 2 is the stronger model overall, scoring 38.8 to 37.7 on the Noometry Index.
Which is cheaper, Mercury 2 or Nova Premier 1.0?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 128K.
How many benchmarks do Mercury 2 and Nova Premier 1.0 share?
0 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Nova Premier 1.0 has 6.