Model A

Inception

—

Evidence status unavailable

90% interval unavailable

Mercury 2.5 vs Qwen3.8 Max

Updated September 8, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

Qwen3.8 Max

Alibaba

71.6/100

Supported · Public rank #11

90% interval 67.9–75.3

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on X LinkedInSocial card CSV JSON

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Long documents
Prompts that approach the documented context limit
Qwen3.8 Max
Qwen3.8 Max has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Mercury 2.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Mercury 2.5 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 Mercury 2.5 only

2 Shared

58 Qwen3.8 Max only

Shared results: 2
Mercury 2.5 only: 3
Qwen3.8 Max only: 58
Like-for-like categories: 1 / 8

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Instruction following

Like-for-like

Mercury 2.5: 80.1; #53/121
Qwen3.8 Max: 90.7; #18/121
Basis: Provisional lane · 1 vs 1 weighted rows
Reading: Qwen3.8 Max leads

Agentic

Directional only

Mercury 2.5: 44.5; Estimated · #91/152
Qwen3.8 Max: 67.2; Supported · #9/152
Basis: BenchAlign lane · 2 vs 15 public rows
Reading: Directional only

Coding

Directional only

Mercury 2.5: 47.8; Estimated · #73/151
Qwen3.8 Max: 60.8; Supported · #20/151
Basis: BenchAlign lane · 1 vs 12 public rows
Reading: Directional only

Knowledge

Directional only

Mercury 2.5: 48.3; Estimated · #94/182
Qwen3.8 Max: 68.8; Supported · #17/182
Basis: BenchAlign lane · 1 vs 6 public rows
Reading: Directional only

Reasoning

Not comparable

Mercury 2.5: 67.7; Unranked · 1 rankable row
Qwen3.8 Max: 86.5; Unranked · 2 rankable rows
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Math

Not comparable

Mercury 2.5: Not ranked
Qwen3.8 Max: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Mercury 2.5: Not ranked
Qwen3.8 Max: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Multimodal

Not comparable

Mercury 2.5: Not ranked
Qwen3.8 Max: 87.4; #5/48
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Mercury 2.5 and Qwen3.8 Max
Category	Mercury 2.5	Qwen3.8 Max	Basis	Reading
Instruction following	80.1#53/121	90.7#18/121	Like-for-likeProvisional lane · 1 vs 1 weighted rows	Qwen3.8 Max leads
Agentic	44.5Estimated · #91/152	67.2Supported · #9/152	Directional onlyBenchAlign lane · 2 vs 15 public rows	Directional only
Coding	47.8Estimated · #73/151	60.8Supported · #20/151	Directional onlyBenchAlign lane · 1 vs 12 public rows	Directional only
Knowledge	48.3Estimated · #94/182	68.8Supported · #17/182	Directional onlyBenchAlign lane · 1 vs 6 public rows	Directional only
Reasoning	67.7Unranked · 1 rankable row	86.5Unranked · 2 rankable rows	Not comparableProvisional lane · 0 vs 2 weighted rows	Not comparable
Math	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Multimodal	Not ranked	87.4#5/48	Not comparableProvisional lane · 0 vs 2 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

IFBench
Instruction following
Mercury 2.5: 77%Qwen3.8 Max: 82.8%Normalized gap 5.8Mercury 2.5 source Qwen3.8 Max source

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Mercury 2.5: $0.00012; Fits in one request
Qwen3.8 Max: API rate not published; Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Mercury 2.5: $0.00245; Fits in one request
Qwen3.8 Max: API rate not published; Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Mercury 2.5: $0.0031; Fits in one request
Qwen3.8 Max: API rate not published; Fits in one request; Cached-input rate unavailable

Qwen3.8 Max has no comparable published API token rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationMercury 2.5Qwen3.8 Max

Context window

Maximum documented context; output-token limits may be lower.

Mercury 2.5

260K

Inception models and Mercury 2.5 launch pricing

Qwen3.8 Max

Alibaba Cloud Model Studio pricing

API model ID

Mercury 2.5

mercury-2.5

Inception models and Mercury 2.5 launch pricing

Qwen3.8 Max

qwen3.8-max

Alibaba Cloud Model Studio pricing

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Mercury 2.5

$0.004 per 1M cached input tokens

Inception models and Mercury 2.5 launch pricing

Qwen3.8 Max

No comparable hosted API rate

Alibaba Cloud Model Studio pricing

Documented inputs

Mercury 2.5

Not sourced

Qwen3.8 Max

Not sourced

Documented outputs

Mercury 2.5

Not sourced

Qwen3.8 Max

Not sourced

Provider availability

Mercury 2.5

Not sourced

Qwen3.8 Max

Not sourced

Reasoning profile

Mercury 2.5

Reasoning

Qwen3.8 Max

Reasoning

Weight access

Mercury 2.5

Proprietary

Qwen3.8 Max

Open Weight

License

Mercury 2.5

Proprietary

Qwen3.8 Max

Open Weight

Release date

Mercury 2.5

2026-09-08

Qwen3.8 Max

2026-08-03

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Qwen3.8 Max has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence63 rows

Agentic

τ³-bench results
Mercury 2.596.0%
Source
Qwen3.8 Max—
Not directly comparable
DeepSearchQA
Mercury 2.534.0%
Source
Qwen3.8 Max—
Not directly comparable
Terminal-Bench 2.1
Mercury 2.5—
Qwen3.8 Max86.6%
Source
Not directly comparable
CoWorkBench
Mercury 2.5—
Qwen3.8 Max74.8%
Source
Not directly comparable
JobBench
Mercury 2.5—
Qwen3.8 Max53.4%
Source
Not directly comparable
skillsBench
Mercury 2.5—
Qwen3.8 Max70.2%
Source
Not directly comparable
Agents' Last Exam
Mercury 2.5—
Qwen3.8 Max52.4%
Source
Not directly comparable
AutomationBench
Mercury 2.5—
Qwen3.8 Max27.3%
Source
Not directly comparable
Toolathlon-Verified
Mercury 2.5—
Qwen3.8 Max72.5%
Source
Not directly comparable
WideResearch
Mercury 2.5—
Qwen3.8 Max81.9%
Source
Not directly comparable
HLE w/ tools
Mercury 2.5—
Qwen3.8 Max56.2%
Source
Not directly comparable
OSWorld-Verified
Mercury 2.5—
Qwen3.8 Max86.1%
Source
Not directly comparable
OSWorld 2.0
Mercury 2.5—
Qwen3.8 Max19.4%
Source
Not directly comparable
WebArena-Verified
Mercury 2.5—
Qwen3.8 Max66.8%
Source
Not directly comparable
AndroidWorld
Mercury 2.5—
Qwen3.8 Max85.3%
Source
Not directly comparable
MobileWorld
Mercury 2.5—
Qwen3.8 Max77.8%
Source
Not directly comparable
Terminal-Bench 2.1 (Vals)
Mercury 2.5—
Qwen3.8 Max67.4%
Source
Not directly comparable

Coding

SciCode
Mercury 2.538%
Source
Qwen3.8 Max—
Not directly comparable
Terminal-Bench 2.1
Mercury 2.5—
Qwen3.8 Max86.6%
Source
Not directly comparable
SWE-bench Pro
Mercury 2.5—
Qwen3.8 Max67.7%
Source
Not directly comparable
deepSwe
Mercury 2.5—
Qwen3.8 Max56.6%
Source
Not directly comparable
NL2Repo
Mercury 2.5—
Qwen3.8 Max55.9%
Source
Not directly comparable
FrontierSWE
Mercury 2.5—
Qwen3.8 Max73.5%
Source
Not directly comparable
MLS-Bench Lite
Mercury 2.5—
Qwen3.8 Max41.0%
Source
Not directly comparable
PaperBench
Mercury 2.5—
Qwen3.8 Max93.0%
Source
Not directly comparable
VulcanBench v3
Mercury 2.5—
Qwen3.8 Max81.2%
Source
Not directly comparable
OpenHarmony Bench
Mercury 2.5—
Qwen3.8 Max60.8%
Source
Not directly comparable
FrontierSWE v2
Mercury 2.5—
Qwen3.8 Max15.8%
Source
Not directly comparable
LiveCodeBench (Vals)
Mercury 2.5—
Qwen3.8 Max87.9%
Source
Not directly comparable
SWE-bench (Vals)
Mercury 2.5—
Qwen3.8 Max85.6%
Source
Not directly comparable

Reasoning

MRCRv2
Mercury 2.5—
Qwen3.8 Max92.9%
Source
Not directly comparable
LongBench v2
Mercury 2.5—
Qwen3.8 Max66.3%
Source
Not directly comparable

Knowledge

GPQA-D
Mercury 2.579.0%
Source
Qwen3.8 Max92.6%
Source
Qwen3.8 Max leads this result
GPQA
Mercury 2.5—
Qwen3.8 Max92.6%
Source
Not directly comparable
HLE
Mercury 2.5—
Qwen3.8 Max43.6%
Source
Not directly comparable
HLE w/o tools
Mercury 2.5—
Qwen3.8 Max43.6%
Source
Not directly comparable
GPQA Diamond (Vals)
Mercury 2.5—
Qwen3.8 Max93.7%
Source
Not directly comparable
MMLU-Pro (Vals)
Mercury 2.5—
Qwen3.8 Max88.6%
Source
Not directly comparable

Multimodal

MMMU-Pro
Mercury 2.5—
Qwen3.8 Max82.3%
Source
Not directly comparable
MathVision
Mercury 2.5—
Qwen3.8 Max95.2%
Source
Not directly comparable
MathVision w/ Python
Mercury 2.5—
Qwen3.8 Max97.7%
Source
Not directly comparable
BabyVision
Mercury 2.5—
Qwen3.8 Max82.0%
Source
Not directly comparable
BabyVision w/ Python
Mercury 2.5—
Qwen3.8 Max91.3%
Source
Not directly comparable
ZeroBench
Mercury 2.5—
Qwen3.8 Max24.0%
Source
Not directly comparable
ZeroBench w/ Python
Mercury 2.5—
Qwen3.8 Max49.0%
Source
Not directly comparable
MedXpertQA (MM)
Mercury 2.5—
Qwen3.8 Max80.4%
Source
Not directly comparable
ScreenSpot Pro
Mercury 2.5—
Qwen3.8 Max84.5%
Source
Not directly comparable
Vision2Web
Mercury 2.5—
Qwen3.8 Max69.0%
Source
Not directly comparable
CharXiv w/o tools
Mercury 2.5—
Qwen3.8 Max88.4%
Source
Not directly comparable
CharXiv
Mercury 2.5—
Qwen3.8 Max93.5%
Source
Not directly comparable
OmniDocBench 1.5
Mercury 2.5—
Qwen3.8 Max92.1%
Source
Not directly comparable
OCRBench V2
Mercury 2.5—
Qwen3.8 Max74.2%
Source
Not directly comparable
CC-OCR
Mercury 2.5—
Qwen3.8 Max79.6%
Source
Not directly comparable
RealWorldQA
Mercury 2.5—
Qwen3.8 Max88.0%
Source
Not directly comparable
ERQA
Mercury 2.5—
Qwen3.8 Max77.8%
Source
Not directly comparable
SimpleVQA
Mercury 2.5—
Qwen3.8 Max75.0%
Source
Not directly comparable
PerceptionBench
Mercury 2.5—
Qwen3.8 Max63.5%
Source
Not directly comparable
Video-MME (with subtitle)
Mercury 2.5—
Qwen3.8 Max90.4%
Source
Not directly comparable
VideoMMMU
Mercury 2.5—
Qwen3.8 Max88.7%
Source
Not directly comparable
MMVU
Mercury 2.5—
Qwen3.8 Max82.4%
Source
Not directly comparable
MLVU (M-Avg)
Mercury 2.5—
Qwen3.8 Max90.8%
Source
Not directly comparable
LVBench
Mercury 2.5—
Qwen3.8 Max81.8%
Source
Not directly comparable

Instruction following

IFBench
Mercury 2.577%
Source
Qwen3.8 Max82.8%
Source
Qwen3.8 Max leads this result

Frequently asked questions

Which is better, Mercury 2.5 or Qwen3.8 Max?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Mercury 2.5 or Qwen3.8 Max?

Qwen3.8 Max scores higher for coding on the public lane, 60.8 to 47.8. Mercury 2.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Mercury 2.5 or Qwen3.8 Max?

Qwen3.8 Max scores higher for agentic tasks on the public lane, 67.2 to 44.5. Mercury 2.5 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Mercury 2.5 or Qwen3.8 Max?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Mercury 2.5 or Qwen3.8 Max?

Qwen3.8 Max has the larger documented context window: 1M, compared with 260K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 8, 2026

Watch Mercury 2.5 vs Qwen3.8 Max

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Mercury 2.5 vs Qwen3.8 Max

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

What is actually comparable

Category results, on a stated basis

Instruction following

Agentic

Coding

Knowledge

Reasoning

Math

Multilingual

Multimodal

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Multimodal

Instruction following

Frequently asked questions

Which is better, Mercury 2.5 or Qwen3.8 Max?

Which is better for coding, Mercury 2.5 or Qwen3.8 Max?

Which is better for agentic tasks, Mercury 2.5 or Qwen3.8 Max?

Which costs less, Mercury 2.5 or Qwen3.8 Max?

Which has the larger context window, Mercury 2.5 or Qwen3.8 Max?

Related comparisons

Watch Mercury 2.5 vs Qwen3.8 Max