Model comparison
Llama 4 Scout vs Mercury 2
Mercury 2 is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.5× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Llama 4 Scout 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 54.0 to 37.1.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 38.7% for Mercury 2.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Mercury 2 | |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 27.4 | 38.8 |
| Released | 2025-04-05 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 50K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $0.75 |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Llama 4 Scout: 19.9 (#334), Mercury 2: 33.2 (#250)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| SciCode | 17% | 38.7% |
| LMArena Coding | 1286 | 1391 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1170 |
| WeirdML | — | 43.2% |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 785.58 |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.4 (#109), Mercury 2: —
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mercury 2 leads
Llama 4 Scout: 9.2 (#339), Mercury 2: 23.0 (#170)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| CritPt | 0% | 0.8% |
| LMArena Hard Prompts | 1266 | 1362 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Not comparable
Llama 4 Scout: 18.4 (#280), Mercury 2: —
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| LMArena Math | 1286 | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Mercury 2 leads
Llama 4 Scout: 31.8 (#208), Mercury 2: 35.6 (#170)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 7.7% | 12.3% |
| LMArena Expert | 1236 | 1358 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Mercury 2: —
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Mercury 2 leads
Llama 4 Scout: 41.3 (#207), Mercury 2: 46.8 (#153)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1253 | 1331 |
| LMArena Chinese | 1256 | 1416 |
| LMArena Russian | 1263 | 1303 |
| LMArena French | 1283 | — |
| LMArena German | 1274 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1207 | — |
| LMArena Spanish | 1277 | — |
Instruction Following Mercury 2 leads
Llama 4 Scout: 66.0 (#212), Mercury 2: 70.4 (#161)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1328 |
| IFEval | 81.8% | — |
Long Context Mercury 2 leads
Llama 4 Scout: 27.5 (#289), Mercury 2: 40.4 (#149)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1265 | 1329 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mercury 2 leads
Llama 4 Scout: 37.1 (#256), Mercury 2: 54.0 (#151)
| Benchmark | Llama 4 Scout | Mercury 2 |
|---|---|---|
| LMArena Text | 1279 | 1355 |
| LMArena Creative Writing | 1249 | 1289 |
| LMArena Multi-Turn | 1281 | 1358 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.5× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mercury 2?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Llama 4 Scout or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.2 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama 4 Scout and Mercury 2 share?
14 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mercury 2 has 17.