Model comparison
Llama 3.2 3B vs Mercury 2.5
Llama 3.2 3B has enough public results to be ranked (#318); Mercury 2.5 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in math, where Llama 3.2 3B leads 29.9 to 22.4.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
- Mercury 2.5 accepts more context: 260K tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 3B | Mercury 2.5 | |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 28.4 | 30.2 |
| Released | 2024-09-24 | 2026-09-08 |
| Weights | Open | Proprietary |
| Context window | 131K | 260K |
| Max output | 118K | 66K |
| Input $ / M tokens | $0.05 | $0.04 |
| Output $ / M tokens | $0.33 | $0.15 |
| Results tracked | 18 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 3B: 27.1 (#314), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| BigCodeBench Instruct | 23.4% | — |
| LMArena Coding | 1098 | — |
| BigCodeBench Complete | 28.3% | — |
| ALE-Bench | — | 301.65 |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Not comparable
Llama 3.2 3B: 20.1 (#225), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Hard Prompts | 1095 | — |
Math Llama 3.2 3B leads
Llama 3.2 3B: 29.9 (#213), Mercury 2.5: 22.4
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | 1126 | — |
Knowledge Not comparable
Llama 3.2 3B: 29.1 (#232), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Expert | 1090 | — |
Multilingual Not comparable
Llama 3.2 3B: 26.4 (#276), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |
Instruction Following Not comparable
Llama 3.2 3B: 56.3 (#270), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1089 | — |
Long Context Not comparable
Llama 3.2 3B: 33.4 (#256), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1101 | — |
Writing & Preference Not comparable
Llama 3.2 3B: 24.9 (#302), Mercury 2.5: —
| Benchmark | Llama 3.2 3B | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1094 | — |
| EQ-Bench Creative Writing | 595 | — |
| LMArena Multi-Turn | 1105 | — |
Frequently asked questions
Is Llama 3.2 3B better than Mercury 2.5?
Llama 3.2 3B has enough public results to be ranked (#318); Mercury 2.5 does not yet, so treat this comparison as directional.
Which is cheaper, Llama 3.2 3B or Mercury 2.5?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.
Which has the bigger context window?
Mercury 2.5 does, with 260K tokens against 131K.
How many benchmarks do Llama 3.2 3B and Mercury 2.5 share?
0 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mercury 2.5 has 2.