Mercury 2.5 vs Qwen3.5-Flash
Qwen3.5-Flash leads Mercury 2.5 on coding, 41.1 to 1.6 on the Vibe Coding Index, and Mercury 2.5 costs 1.7x less per output token ($0.15 vs $0.26 per million). Updated October 22, 2026; 4 benchmarks have a result for both.
Mercury 2.5 or Qwen3.5-Flash: which to pick
Pick Qwen3.5-Flash for coding: it scores 41.1 on the Vibe Coding Index against 1.6 for Mercury 2.5.
Pick Mercury 2.5 for output tokens 1.7x cheaper ($0.15 vs $0.26 per million) and work measured by ALE-Bench, where it leads.
- Shared results
- 4
- Mercury 2.5 only
- 18
- Qwen3.5-Flash only
- 51
- Like-for-like categories
- 3 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
Qwen3.5-Flash
Qwen3.5-Flash scores 41.1 against 1.6.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only Mercury 2.5 has a AA Intelligence Index result, 12.3.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.5-Flash has a GPQA Diamond result, 82.8%.
Directional only
Math
AIME
No call
Only Qwen3.5-Flash has a AIME result, 92.5%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.5-Flash has a MMLU Pro result, 84.1%.
Directional only
Long documents
Listed context window
Qwen3.5-Flash
Qwen3.5-Flash takes 1M tokens against 260K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
Mercury 2.5 $0.0001, Qwen3.5-Flash $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.5-Flash has the number, $0.40.
Directional only
At a glance
- Coding index
- Mercury 2.5 1.6 from 2 benchmarks, Qwen3.5-Flash 41.1 from 2 benchmarks.
- Widest category
- General, 15.5 points apart on average over 1 shared benchmark.
- Widest single gap
- MedScribe (Vals AI): Mercury 2.5 55.1% against Qwen3.5-Flash 70.6%, 15.5 points apart on a 0 to 100 scale.
- Output price
- Mercury 2.5 $0.15 against Qwen3.5-Flash $0.26 per million output tokens, 1.7x apart.
- Context window
- Mercury 2.5 takes 260K tokens, Qwen3.5-Flash 1M.
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 2.5 | Bars | Qwen3.5-Flash | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Knowledge | 0 | 2 | ||
| General | 0 | 1 | ||
| All shared boards | 1 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1244 | Only Qwen3.5-Flash measured |
| LiveCodeBench (Vals AI) | Not measured | 83.3% | Only Qwen3.5-Flash measured |
| SWE-bench Verified (Vals AI) | Not measured | 64.4% | Only Qwen3.5-Flash measured |
| Terminal-Bench 4 (Vals AI) | 0.0% | Not measured | Only Mercury 2.5 measured |
| Vibe Code Bench (Vals AI) | 3.7% | Not measured | Only Mercury 2.5 measured |
| Code migration (Vals AI) | 4.5% | Not measured | Only Mercury 2.5 measured |
| IOI (Vals AI) | 2.4% | Not measured | Only Mercury 2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 34.5% | Not measured | Only Mercury 2.5 measured |
| SkillsBench (Vals AI) | 18.1% | Not measured | Only Mercury 2.5 measured |
| CyberBench (Vals AI) | 45.5% | Not measured | Only Mercury 2.5 measured |
| SciCode | 38.5% | Not measured | Only Mercury 2.5 measured |
| ALE-Bench | 301.6 | 265.9 | Mercury 2.5 |
| LMArena Text: coding | Not measured | 1412 | Only Qwen3.5-Flash measured |
| LMArena Text: software and IT | Not measured | 1416 | Only Qwen3.5-Flash measured |
| LMArena WebDev: React | Not measured | 1229 | Only Qwen3.5-Flash measured |
| LMArena WebDev: HTML | Not measured | 1291 | Only Qwen3.5-Flash measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.3 | Not measured | Only Mercury 2.5 measured |
| Epoch Capabilities Index | Not measured | 143.5 | Only Qwen3.5-Flash measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | 18.9% | Not measured | Only Mercury 2.5 measured |
| Tax Agent Bench (Vals AI) | 2.5% | Not measured | Only Mercury 2.5 measured |
| Legal Research Bench (Vals AI) | 4.3% | Not measured | Only Mercury 2.5 measured |
| Excel Modeling Benchmark (Vals AI) | 8.8% | Not measured | Only Mercury 2.5 measured |
| Terminal-Bench-Science (Vals AI) | 0.0% | Not measured | Only Mercury 2.5 measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 82.8% | Only Qwen3.5-Flash measured |
| MMMU Pro (Vals AI) | Not measured | 81.9% | Only Qwen3.5-Flash measured |
| Humanity's Last Exam (Artificial Analysis run) | 11.8% | Not measured | Only Mercury 2.5 measured |
| GPQA Diamond (Epoch AI run) | Not measured | 82.3% | Only Qwen3.5-Flash measured |
| Chess puzzles | Not measured | 14.0% | Only Qwen3.5-Flash measured |
| Mystery game puzzles | Not measured | 20.0% | Only Qwen3.5-Flash measured |
| LMArena Text: hard prompts | Not measured | 1403 | Only Qwen3.5-Flash measured |
| LMArena Text: expert | Not measured | 1407 | Only Qwen3.5-Flash measured |
| LMArena Text: hard prompts in English | Not measured | 1409 | Only Qwen3.5-Flash measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AIME | Not measured | 92.5% | Only Qwen3.5-Flash measured |
| OTIS Mock AIME | Not measured | 84.4% | Only Qwen3.5-Flash measured |
| FrontierMath, tiers 1 to 3 | Not measured | 18.2% | Only Qwen3.5-Flash measured |
| ProofBench | 3.0% | Not measured | Only Mercury 2.5 measured |
| LMArena Text: math | Not measured | 1407 | Only Qwen3.5-Flash measured |
| LMArena Text: mathematical work | Not measured | 1413 | Only Qwen3.5-Flash measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.1% | Only Qwen3.5-Flash measured |
| LegalBench (Vals AI) | 83.1% | 84.3% | Qwen3.5-Flash |
| CaseLaw (Vals AI) | Not measured | 56.0% | Only Qwen3.5-Flash measured |
| CorpFin (Vals AI) | Not measured | 63.6% | Only Qwen3.5-Flash measured |
| TaxEval (Vals AI) | Not measured | 72.2% | Only Qwen3.5-Flash measured |
| MortgageTax (Vals AI) | Not measured | 67.4% | Only Qwen3.5-Flash measured |
| MedCode (Vals AI) | 31.3% | 33.0% | Qwen3.5-Flash |
| SimpleQA Verified | Not measured | 20.3% | Only Qwen3.5-Flash measured |
| LMArena Text: science | Not measured | 1415 | Only Qwen3.5-Flash measured |
| LMArena Text: medicine and healthcare | Not measured | 1407 | Only Qwen3.5-Flash measured |
| LMArena Text: legal and government | Not measured | 1398 | Only Qwen3.5-Flash measured |
| LMArena Text: business and finance | Not measured | 1394 | Only Qwen3.5-Flash measured |
| Neither model has a result on the other 8 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 45.3% | Not measured | Only Mercury 2.5 measured |
| SAGE (Vals AI) | Not measured | 42.5% | Only Qwen3.5-Flash measured |
| MedScribe (Vals AI) | 55.1% | 70.6% | Qwen3.5-Flash |
| Long context reasoning (AA-LCR) | 71.7% | Not measured | Only Mercury 2.5 measured |
| DTBench | Not measured | 82.9% | Only Qwen3.5-Flash measured |
| LMCA | Not measured | 29.1% | Only Qwen3.5-Flash measured |
| LMArena Text | Not measured | 1397 | Only Qwen3.5-Flash measured |
| LMArena Text: instruction following | Not measured | 1374 | Only Qwen3.5-Flash measured |
| LMArena Text: creative writing | Not measured | 1343 | Only Qwen3.5-Flash measured |
| LMArena Text: English | Not measured | 1404 | Only Qwen3.5-Flash measured |
| LMArena Text: non-English | Not measured | 1385 | Only Qwen3.5-Flash measured |
| LMArena Text: Chinese | Not measured | 1445 | Only Qwen3.5-Flash measured |
| LMArena Text: German | Not measured | 1390 | Only Qwen3.5-Flash measured |
| LMArena Text: Japanese | Not measured | 1369 | Only Qwen3.5-Flash measured |
| LMArena Text: Korean | Not measured | 1344 | Only Qwen3.5-Flash measured |
| LMArena Text: French | Not measured | 1413 | Only Qwen3.5-Flash measured |
| LMArena Text: Spanish | Not measured | 1400 | Only Qwen3.5-Flash measured |
| LMArena Text: Russian | Not measured | 1380 | Only Qwen3.5-Flash measured |
| LMArena Text: Polish | Not measured | 1376 | Only Qwen3.5-Flash measured |
| LMArena Text: multi-turn | Not measured | 1393 | Only Qwen3.5-Flash measured |
| LMArena Text: longer queries | Not measured | 1392 | Only Qwen3.5-Flash measured |
| LMArena Text: writing and language | Not measured | 1369 | Only Qwen3.5-Flash measured |
| LMArena Text: entertainment and media | Not measured | 1347 | Only Qwen3.5-Flash measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2.5 | Qwen3.5-Flash | 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
Mercury 2.5 costs less
Repository review
50K input + 3K output tokens
Mercury 2.5 costs less
Agent loop
200K input + 10K output tokens
Mercury 2.5 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 2.5 | Qwen3.5-Flash |
|---|---|---|
| Maker | Inception | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | September 8, 2026 | February 25, 2026 |
| Context window | 260K | 1M |
| Input $/Mtok | $0.04 | $0.065 |
| Output $/Mtok | $0.15 | $0.26 |
| Coding index | 1.6 | 41.1 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $0.40 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 2.5 better than Qwen3.5-Flash for coding?
Pick Qwen3.5-Flash for coding: it scores 41.1 on the Vibe Coding Index against 1.6 for Mercury 2.5. Pick Mercury 2.5 for output tokens 1.7x cheaper ($0.15 vs $0.26 per million) and work measured by ALE-Bench, where it leads.
Which is cheaper, Mercury 2.5 or Qwen3.5-Flash?
Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens; Qwen3.5-Flash costs $0.065 and $0.26. Cost per solved task is known for Qwen3.5-Flash only.
Which has the bigger context window, Mercury 2.5 or Qwen3.5-Flash?
Qwen3.5-Flash, with 1M tokens against 260K.
How many benchmarks is the Mercury 2.5 vs Qwen3.5-Flash comparison based on?
4 benchmarks have a result for both models as of October 22, 2026. Mercury 2.5's coding index rests on 2 independent benchmarks and Qwen3.5-Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.