Model comparison
Claude 3 Sonnet vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 21.1.
- The biggest single-benchmark swing is WeirdML: 10.2% for Claude 3 Sonnet and 43.2% for Mercury 2.
Side by side
| Claude 3 Sonnet | Mercury 2 | |
|---|---|---|
| Provider | Anthropic | Inception |
| Noometry Index | 29.0 | 39.1 |
| Released | 2024-02-29 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 30 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Claude 3 Sonnet: 29.6 (#302), Mercury 2: 33.5 (#255)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| WeirdML | 10.2% | 43.2% |
| LMArena Coding | 1223 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Mercury 2 leads
Claude 3 Sonnet: 20.5 (#237), Mercury 2: 23.8 (#170)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1362 |
| CritPt | — | 0.8% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Not comparable
Claude 3 Sonnet: 10.7 (#310), Mercury 2: —
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |
Knowledge Mercury 2 leads
Claude 3 Sonnet: 21.1 (#276), Mercury 2: 36.2 (#172)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Expert | 1173 | 1358 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 12.3% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Mercury 2: —
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Mercury 2 leads
Claude 3 Sonnet: 37.8 (#234), Mercury 2: 46.6 (#157)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1205 | 1331 |
| LMArena Chinese | 1189 | 1417 |
| LMArena Russian | 1227 | 1304 |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Mercury 2 leads
Claude 3 Sonnet: 62.8 (#235), Mercury 2: 70.2 (#165)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1329 |
Long Context Mercury 2 leads
Claude 3 Sonnet: 36.7 (#228), Mercury 2: 40.5 (#154)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1211 | 1330 |
Writing & Preference Mercury 2 leads
Claude 3 Sonnet: 42.1 (#238), Mercury 2: 53.8 (#155)
| Benchmark | Claude 3 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Text | 1218 | 1355 |
| LMArena Creative Writing | 1186 | 1289 |
| LMArena Multi-Turn | 1227 | 1358 |
Frequently asked questions
Is Claude 3 Sonnet better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Mercury 2 share?
12 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Mercury 2 has 17.