Model comparison
Claude Sonnet 4 vs Mercury 2
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 38.8 on the Noometry Index. Mercury 2 costs 16× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and Mercury 2 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4 leads 44.0 to 33.2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 128K.
Side by side
| Claude Sonnet 4 | Mercury 2 | |
|---|---|---|
| Provider | Anthropic | Inception |
| Noometry Index | 40.6 | 38.8 |
| Released | 2025-05-22 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 128K |
| Max output | 64K | 50K |
| Input $ / M tokens | $3 | $0.25 |
| Output $ / M tokens | $15 | $0.75 |
| Results tracked | 58 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), Mercury 2: 33.2 (#250)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| SciCode | 40% | 38.7% |
| WeirdML | 46.1% | 43.2% |
| LMArena Coding | 1414 | 1391 |
| ALE-Bench | 655.35 | 785.58 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1170 |
| GSO | 4.9% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.3 (#29), Mercury 2: —
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Too close to call
Claude Sonnet 4: 23.0 (#169), Mercury 2: 23.0 (#170)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| CritPt | 0.3% | 0.8% |
| LMArena Hard Prompts | 1372 | 1362 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Not comparable
Claude Sonnet 4: 41.5 (#71), Mercury 2: —
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| LMArena Math | 1375 | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.6 (#99), Mercury 2: 35.6 (#170)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 12.3% |
| LMArena Expert | 1371 | 1358 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), Mercury 2: —
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Too close to call
Claude Sonnet 4: 46.9 (#151), Mercury 2: 46.8 (#153)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1333 | 1331 |
| LMArena Chinese | 1351 | 1416 |
| LMArena Russian | 1355 | 1303 |
| LMArena French | 1364 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1301 | — |
| LMArena Korean | 1293 | — |
| LMArena Spanish | 1356 | — |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.8 (#141), Mercury 2: 70.4 (#161)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1375 | 1328 |
| IFEval | 84% | — |
Long Context Mercury 2 leads
Claude Sonnet 4: 33.6 (#254), Mercury 2: 40.4 (#149)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1398 | 1329 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.3 (#127), Mercury 2: 54.0 (#151)
| Benchmark | Claude Sonnet 4 | Mercury 2 |
|---|---|---|
| LMArena Text | 1351 | 1355 |
| LMArena Creative Writing | 1345 | 1289 |
| LMArena Multi-Turn | 1376 | 1358 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Mercury 2?
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 38.8 on the Noometry Index. Mercury 2 costs 16× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Mercury 2 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 128K.
How many benchmarks do Claude Sonnet 4 and Mercury 2 share?
16 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Mercury 2 has 17.