Model comparison
Claude 3 Haiku vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 25.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 29.7.
- The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 43.2% for Mercury 2.
Side by side
| Claude 3 Haiku | Mercury 2 | |
|---|---|---|
| Provider | Anthropic | Inception |
| Noometry Index | 25.9 | 39.1 |
| Released | 2024-03-07 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 37 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Claude 3 Haiku: 26.4 (#325), Mercury 2: 33.5 (#255)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| WeirdML | 9.8% | 43.2% |
| LMArena Coding | 1199 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Mercury 2 leads
Claude 3 Haiku: 16.3 (#307), Mercury 2: 23.8 (#170)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1362 |
| Kagi LLM Benchmark | 34.2% | — |
| CritPt | — | 0.8% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Not comparable
Claude 3 Haiku: 9.8 (#319), Mercury 2: —
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Mercury 2 leads
Claude 3 Haiku: 17.3 (#285), Mercury 2: 36.2 (#172)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Expert | 1148 | 1358 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 12.3% |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Mercury 2: —
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Mercury 2 leads
Claude 3 Haiku: 36.0 (#243), Mercury 2: 46.6 (#157)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1178 | 1331 |
| LMArena Chinese | 1155 | 1417 |
| LMArena Russian | 1204 | 1304 |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Mercury 2 leads
Claude 3 Haiku: 61.3 (#247), Mercury 2: 70.2 (#165)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1329 |
Long Context Mercury 2 leads
Claude 3 Haiku: 36.1 (#237), Mercury 2: 40.5 (#154)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1190 | 1330 |
Writing & Preference Mercury 2 leads
Claude 3 Haiku: 29.7 (#291), Mercury 2: 53.8 (#155)
| Benchmark | Claude 3 Haiku | Mercury 2 |
|---|---|---|
| LMArena Text | 1195 | 1355 |
| LMArena Creative Writing | 1157 | 1289 |
| LMArena Multi-Turn | 1190 | 1358 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Mercury 2 share?
12 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mercury 2 has 17.