Model comparison
Mercury 2 vs Qwen3 8B
Mercury 2 is the stronger model overall, scoring 38.8 to 33.3 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Mercury 2 scores higher in 2 categories and Qwen3 8B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.0 to 16.1.
- The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 22.6% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Qwen3 8B accepts more context: 131K tokens versus 128K.
- Qwen3 8B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen3 8B | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 33.3 |
| Released | 2026-02-20 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 50K | 8K |
| Input $ / M tokens | $0.25 | $0.18 |
| Output $ / M tokens | $0.75 | $0.70 |
| Results tracked | 17 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.2 (#250), Qwen3 8B: 33.4 (#245)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| SciCode | 38.7% | 22.6% |
| LMArena WebDev | 1170 | — |
| WeirdML | 43.2% | — |
| LMArena Coding | 1391 | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen3 8B: 29.9 (#71)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Qwen3 8B: 16.1 (#299)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| CritPt | 0.8% | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1362 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math Not comparable
Mercury 2: —, Qwen3 8B: 33.3 (#176)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
Knowledge Too close to call
Mercury 2: 35.6 (#170), Qwen3 8B: 36.1 (#164)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 4.8% |
| GPQA Diamond | — | 56.8% |
| LMArena Expert | 1358 | — |
Multilingual Not comparable
Mercury 2: 46.8 (#153), Qwen3 8B: —
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |
Instruction Following Not comparable
Mercury 2: 70.4 (#161), Qwen3 8B: —
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1328 | — |
Long Context Mercury 2 leads
Mercury 2: 40.4 (#149), Qwen3 8B: 37.8 (#205)
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1329 | — |
Writing & Preference Not comparable
Mercury 2: 54.0 (#151), Qwen3 8B: —
| Benchmark | Mercury 2 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| LMArena Multi-Turn | 1358 | — |
Frequently asked questions
Is Mercury 2 better than Qwen3 8B?
Mercury 2 is the stronger model overall, scoring 38.8 to 33.3 on the Noometry Index.
Which is cheaper, Mercury 2 or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Mercury 2 or Qwen3 8B better for coding?
They score almost the same on coding (33.2 vs 33.4); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3 8B does, with 131K tokens against 128K.
How many benchmarks do Mercury 2 and Qwen3 8B share?
3 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3 8B has 11.