Model comparison
Claude 3.5 Sonnet vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 34.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Mercury 2 in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 28.6.
Side by side
| Claude 3.5 Sonnet | Mercury 2 | |
|---|---|---|
| Provider | Anthropic | Inception |
| Noometry Index | 34.6 | 39.1 |
| Released | 2024-06-20 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 60 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Mercury 2: 33.5 (#255)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| WeirdML | 40% | 43.2% |
| LMArena Coding | 1342 | 1391 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Mercury 2: —
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Too close to call
Claude 3.5 Sonnet: 23.1 (#183), Mercury 2: 23.8 (#170)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1362 |
| SimpleBench | 41.4% | — |
| CritPt | — | 0.8% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Not comparable
Claude 3.5 Sonnet: 19.2 (#288), Mercury 2: —
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| LMArena Math | 1307 | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Mercury 2 leads
Claude 3.5 Sonnet: 28.6 (#245), Mercury 2: 36.2 (#172)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Expert | 1265 | 1358 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Mercury 2: —
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Mercury 2 leads
Claude 3.5 Sonnet: 43.2 (#185), Mercury 2: 46.6 (#157)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1283 | 1331 |
| LMArena Chinese | 1272 | 1417 |
| LMArena Russian | 1306 | 1304 |
| LMArena French | 1305 | — |
| LMArena German | 1297 | — |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
| LMArena Spanish | 1290 | — |
Instruction Following Mercury 2 leads
Claude 3.5 Sonnet: 68.8 (#182), Mercury 2: 70.2 (#165)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1329 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#167), Mercury 2: 40.5 (#154)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1311 | 1330 |
Writing & Preference Too close to call
Claude 3.5 Sonnet: 52.9 (#164), Mercury 2: 53.8 (#155)
| Benchmark | Claude 3.5 Sonnet | Mercury 2 |
|---|---|---|
| LMArena Text | 1298 | 1355 |
| LMArena Creative Writing | 1292 | 1289 |
| LMArena Multi-Turn | 1326 | 1358 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Mercury 2 better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 33.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Mercury 2 share?
12 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Mercury 2 has 17.