Mercury 2 vs Qwen3 30B A3B
Mercury 2 leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 10.8 to 7.6, and Qwen3 30B A3B costs 1.5x less per output token ($0.50 vs $0.75 per million). Updated October 22, 2026; 32 benchmarks have a result for both.
Mercury 2 or Qwen3 30B A3B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mercury 2 for a larger context window (128K against 41K tokens).
- Shared results
- 32
- Mercury 2 only
- 10
- Qwen3 30B A3B only
- 20
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mercury 2
Mercury 2 leads, 10.8 against 7.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mercury 2 has a AA Agentic Index result, 1.6.
Directional only
Web design
Design Arena: websites
Mercury 2
Mercury 2 leads, 1036 against 954.
Same board, both measured
Long documents
Listed context window
Mercury 2
Mercury 2 takes 128K tokens against 41K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 30B A3B
Mercury 2 $0.0006, Qwen3 30B A3B $0.0004 per turn.
List prices
At a glance
- Coding index
- Mercury 2 not benchmarked, Qwen3 30B A3B not benchmarked.
- Widest category
- Agentic work, 44.7 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Mercury 2 70.8% against Qwen3 30B A3B 26.0%, 44.7 points apart on a 0 to 100 scale.
- Output price
- Mercury 2 $0.75 against Qwen3 30B A3B $0.50 per million output tokens, 1.5x apart.
- Context window
- Mercury 2 takes 128K tokens, Qwen3 30B A3B 41K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Mercury 2 | Bars | Qwen3 30B A3B | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Knowledge | 3 | 0 | ||
| Web design | 5 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 32 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| LMArena WebDev | 1171 | Not measured | Only Mercury 2 measured |
| AA Coding Index | 31.1 | Not measured | Only Mercury 2 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 50.6% | Only Qwen3 30B A3B measured |
| SciCode | 37.7% | Not measured | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 6.8% | Mercury 2 |
| WeirdML | 43.2% | 29.8% | Mercury 2 |
| ALE-Bench | 785.6 | Not measured | Only Mercury 2 measured |
| LMArena Text: coding | 1390 | 1337 | Mercury 2 |
| LMArena Text: software and IT | 1385 | 1340 | Mercury 2 |
| LMArena WebDev: React | 1160 | Not measured | Only Mercury 2 measured |
| LMArena WebDev: HTML | 1199 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 7.6 | Mercury 2 |
| Epoch Capabilities Index | Not measured | 137.3 | Only Qwen3 30B A3B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Mercury 2 measured |
| τ²-Bench Telecom | 70.8% | 26.0% | Mercury 2 |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 77.0% | 61.6% | Mercury 2 |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 6.2% | Mercury 2 |
| GPQA Diamond (Epoch AI run) | Not measured | 61.7% | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts | 1362 | 1314 | Mercury 2 |
| LMArena Text: expert | 1358 | 1314 | Mercury 2 |
| LMArena Text: hard prompts in English | 1374 | 1329 | Mercury 2 |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 72.3 | Only Qwen3 30B A3B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 72.3% | Only Qwen3 30B A3B measured |
| OTIS Mock AIME | Not measured | 62.8% | Only Qwen3 30B A3B measured |
| LMArena Text: math | Not measured | 1355 | Only Qwen3 30B A3B measured |
| LMArena Text: mathematical work | Not measured | 1363 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 77.7% | Only Qwen3 30B A3B measured |
| LMArena Text: science | 1343 | 1321 | Mercury 2 |
| LMArena Text: medicine and healthcare | 1363 | 1318 | Mercury 2 |
| LMArena Text: legal and government | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: business and finance | 1349 | 1309 | Mercury 2 |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Design Arena: websites | 1036 | 954 | Mercury 2 |
| Design Arena: UI components | 996 | 943 | Mercury 2 |
| Design Arena: game dev | 984 | 898 | Mercury 2 |
| Design Arena: data viz | 1009 | 967 | Mercury 2 |
| Design Arena: 3D | 982 | Not measured | Only Mercury 2 measured |
| Design Arena: all code categories | 1021 | 941 | Mercury 2 |
| Design Arena: SVG | 998 | Not measured | Only Mercury 2 measured |
| Design Arena: ASCII art | 988 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| IFBench | 69.8% | 41.5% | Mercury 2 |
| Long context reasoning (AA-LCR) | 43.7% | 0.0% | Mercury 2 |
| DTBench | Not measured | 60.3% | Only Qwen3 30B A3B measured |
| LMCA | Not measured | 15.8% | Only Qwen3 30B A3B measured |
| Fiction.LiveBench | Not measured | 40.6% | Only Qwen3 30B A3B measured |
| Creative writing (Lech Mazur) | Not measured | 75.3% | Only Qwen3 30B A3B measured |
| LMArena Text | 1354 | 1317 | Mercury 2 |
| LMArena Text: instruction following | 1328 | 1283 | Mercury 2 |
| LMArena Text: creative writing | 1286 | 1271 | Mercury 2 |
| LMArena Text: English | 1378 | 1335 | Mercury 2 |
| LMArena Text: non-English | 1330 | 1295 | Mercury 2 |
| LMArena Text: Chinese | 1414 | 1347 | Mercury 2 |
| LMArena Text: German | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: Japanese | Not measured | 1254 | Only Qwen3 30B A3B measured |
| LMArena Text: Korean | Not measured | 1261 | Only Qwen3 30B A3B measured |
| LMArena Text: French | Not measured | 1352 | Only Qwen3 30B A3B measured |
| LMArena Text: Spanish | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: Russian | 1304 | 1291 | Mercury 2 |
| LMArena Text: Polish | Not measured | 1299 | Only Qwen3 30B A3B measured |
| LMArena Text: multi-turn | 1357 | 1307 | Mercury 2 |
| LMArena Text: longer queries | 1329 | 1312 | Mercury 2 |
| LMArena Text: writing and language | 1300 | 1290 | Mercury 2 |
| LMArena Text: entertainment and media | 1314 | 1258 | Mercury 2 |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Qwen3 30B A3B costs less
Repository review
50K input + 3K output tokens
Qwen3 30B A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3 30B A3B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Inception Mercury 2 | Qwen3 30B A3B |
|---|---|---|
| Maker | Inception | Qwen |
| Weights | No public weights listed | Open weights |
| Released | March 4, 2026 | April 28, 2025 |
| Context window | 128K | 41K |
| Input $/Mtok | $0.25 | $0.12 |
| Output $/Mtok | $0.75 | $0.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 2 better than Qwen3 30B A3B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mercury 2 for a larger context window (128K against 41K tokens).
Which is cheaper, Mercury 2 or Qwen3 30B A3B?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 2 or Qwen3 30B A3B?
Mercury 2, with 128K tokens against 41K.
How many benchmarks is the Mercury 2 vs Qwen3 30B A3B comparison based on?
32 benchmarks have a result for both models as of October 22, 2026. Mercury 2's coding index rests on 1 independent benchmark and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.