Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Mercury 2.5 vs Step 5 Preview

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.

Inception logo
Model A
Mercury 2.5

Inception

—

Evidence status unavailable

90% interval unavailable

StepFun logo
Model B
Step 5 Preview

StepFun

—

Evidence status unavailable

90% interval unavailable

Updated September 21, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Share or export

Share on XLinkedInSocial cardCSVJSON

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

    Step 5 Preview

    Step 5 Preview has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Mercury 2.5

    Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    Mercury 2.5

    Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Mercury 2.5

    Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Step 5 Preview is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Step 5 Preview is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

41.6Mercury 2.5—Step 5 Preview

Not comparable · BenchAlign

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job

What is actually comparable

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

Shared results
2
Mercury 2.5 only
4
Step 5 Preview only
20
Like-for-like categories
0 / 8

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.

Agentic

Not comparable
Mercury 2.5
37.4
Estimated · #131/154
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 3 vs 11 public rows
Reading
Not comparable

Coding

Not comparable
Mercury 2.5
41.6
Estimated · #113/156
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 1 vs 6 public rows
Reading
Not comparable

Reasoning

Not comparable
Mercury 2.5
67.7
Unranked · 1 rankable row
Step 5 Preview
78.5
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Mercury 2.5
Not ranked
Step 5 Preview
61.2
#28/49
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Mercury 2.5
47.9
Estimated · #97/186
Step 5 Preview
Not ranked
Basis
BenchAlign lane · 1 vs 2 public rows
Reading
Not comparable

Multilingual

Not comparable
Mercury 2.5
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Mercury 2.5
77.7
#56/124
Step 5 Preview
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Mercury 2.5
Not ranked
Step 5 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
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.

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
Step 5 Preview
$0.00235
Fits in one request

Mercury 2.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Mercury 2.5
$0.00245
Fits in one request
Step 5 Preview
$0.0581
Fits in one request

Mercury 2.5 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Mercury 2.5
$0.0031
Fits in one request
Step 5 Preview
$0.057
Fits in one request

Mercury 2.5 has the lower modeled cost

Costs use the listed standard API rates.

Specification differences

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

Reasoning profile

Mercury 2.5

Reasoning

Step 5 Preview

Reasoning

Weight access

Mercury 2.5

Proprietary

Step 5 Preview

Pending

License

Mercury 2.5

Proprietary

Step 5 Preview

Pending

Release date

Mercury 2.5

2026-09-08

Step 5 Preview

2026-09-20

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
Repository review: $0.00245 vs $0.0581. Cache-heavy agent loop: $0.0031 vs $0.057.
Context tradeoff
Step 5 Preview 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 evidence26 rows

Agentic

  • τ³-bench results

    Mercury 2.596.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • DeepSearchQA

    Mercury 2.534.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Mercury 2.534.1%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1

    Mercury 2.5—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Mercury 2.5—
    Step 5 Preview33.30%
    Source

    Not directly comparable

  • CyberGym

    Mercury 2.5—
    Step 5 Preview84.7%
    Source

    Not directly comparable

  • AutomationBench

    Mercury 2.5—
    Step 5 Preview44.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Mercury 2.5—
    Step 5 Preview74.1%
    Source

    Not directly comparable

  • MCP Atlas

    Mercury 2.5—
    Step 5 Preview85.6%
    Source

    Not directly comparable

  • JobBench

    Mercury 2.5—
    Step 5 Preview59.0%
    Source

    Not directly comparable

  • APEX-Agents

    Mercury 2.5—
    Step 5 Preview37.8%
    Source

    Not directly comparable

  • DRACO

    Mercury 2.5—
    Step 5 Preview83.3%
    Source

    Not directly comparable

  • BrowseComp

    Mercury 2.5—
    Step 5 Preview88.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Mercury 2.5—
    Step 5 Preview29.5%
    Source

    Not directly comparable

Coding

  • SciCode

    Mercury 2.538%
    Source
    Step 5 Preview58.9%
    Source

    Step 5 Preview leads this result

  • DeepSWE

    Mercury 2.5—
    Step 5 Preview67.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Mercury 2.5—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • ProgramBench

    Mercury 2.5—
    Step 5 Preview80.5%
    Source

    Not directly comparable

  • sweMarathon

    Mercury 2.5—
    Step 5 Preview72.7%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Mercury 2.5—
    Step 5 Preview40.5%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Mercury 2.5—
    Step 5 Preview20.9%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Mercury 2.5—
    Step 5 Preview60.3%
    Source

    Not directly comparable

  • MMMU-Pro

    Mercury 2.5—
    Step 5 Preview76%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Mercury 2.579.0%
    Source
    Step 5 Preview93.5%
    Source

    Step 5 Preview leads this result

  • HLE

    Mercury 2.5—
    Step 5 Preview46.5%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Mercury 2.577%
    Source
    Step 5 Preview—

    Not directly comparable

Questions

Which is better, Mercury 2.5 or Step 5 Preview?

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 Step 5 Preview?

Step 5 Preview is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Mercury 2.5 or Step 5 Preview?

Step 5 Preview is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Mercury 2.5 or Step 5 Preview?

For the stated presets, chat costs $0.00012 on Mercury 2.5 and $0.00235 on Step 5 Preview; repository review costs $0.00245 and $0.0581; the cache-heavy agent loop costs $0.0031 and $0.057. Costs use the listed standard API rates.

Which has the larger context window, Mercury 2.5 or Step 5 Preview?

Step 5 Preview 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 21, 2026

Watch Mercury 2.5 vs Step 5 Preview

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

Read a sample issue

Join 2,000+ readers.