Model comparison
Mercury 2.5 vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 15× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in math, where Sonar leads 33.7 to 23.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $1 / $1 for Sonar.
- Mercury 2.5 accepts more context: 260K tokens versus 128K.
Side by side
| Mercury 2.5 | Sonar | |
|---|---|---|
| Provider | Inception | Perplexity |
| Noometry Index | 33.5 | 38.5 |
| Released | 2026-09-08 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 260K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.04 | $1 |
| Output $ / M tokens | $0.15 | $1 |
| Results tracked | 4 | 7 |
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), Sonar: 35.7 (#221)
| Benchmark | Mercury 2.5 | Sonar |
|---|---|---|
| SciCode | 38.5% | — |
| LiveBench Coding | — | 35.1% |
| ALE-Bench | 301.65 | — |
Reasoning Mercury 2.5 leads
Mercury 2.5: 22.4 (#193), Sonar: 21.1 (#227)
| Benchmark | Mercury 2.5 | Sonar |
|---|---|---|
| CritPt | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Sonar leads
Mercury 2.5: 23.3 (#272), Sonar: 33.7 (#200)
| Benchmark | Mercury 2.5 | Sonar |
|---|---|---|
| ProofBench | 3% | — |
| LiveBench Math | — | 41.6% |
Instruction Following Not comparable
Mercury 2.5: —, Sonar: 71.4 (#150)
| Benchmark | Mercury 2.5 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Not comparable
Mercury 2.5: —, Sonar: 52.6 (#167)
| Benchmark | Mercury 2.5 | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Mercury 2.5 better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 15× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Mercury 2.5 or Sonar?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Sonar lists at $1 and $1.
Is Mercury 2.5 or Sonar better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Mercury 2.5 does, with 260K tokens against 128K.
How many benchmarks do Mercury 2.5 and Sonar share?
0 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Sonar has 7.