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

GPT-6 Sol vs Mercury 2.5

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

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

OpenAI logo
Model A
GPT-6 Sol

OpenAI

80.45/100

Estimated · Public rank #7

90% interval 51.1–92.0

Inception logo
Model B
Mercury 2.5

Inception

—

Evidence status unavailable

90% interval unavailable

Updated September 22, 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

    GPT-6 Sol

    GPT-6 Sol 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

    GPT-6 Sol and Mercury 2.5 are 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

    GPT-6 Sol and Mercury 2.5 are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    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.

74.3GPT-6 Sol41.8Mercury 2.5

Directional only · BenchAlign

GPT-6 Sol scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

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
0
GPT-6 Sol only
10
Mercury 2.5 only
6
Like-for-like categories
0 / 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.

Agentic

Directional only
GPT-6 Sol
69.7
Estimated · #7/157
Mercury 2.5
37.6
Estimated · #132/157
Basis
BenchAlign lane · 4 vs 3 public rows
Reading
Directional only

Coding

Directional only
GPT-6 Sol
74.3
Estimated · #6/159
Mercury 2.5
41.8
Estimated · #115/159
Basis
BenchAlign lane · 1 vs 1 public rows
Reading
Directional only

Knowledge

Directional only
GPT-6 Sol
80.2
Estimated · #6/189
Mercury 2.5
48.3
Estimated · #99/189
Basis
BenchAlign lane · 5 vs 1 public rows
Reading
Directional only

Reasoning

Not comparable
GPT-6 Sol
78.5
#5/17
Mercury 2.5
67.7
Unranked · 1 rankable row
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GPT-6 Sol
82.8
Unranked · 1 rankable row
Mercury 2.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
GPT-6 Sol
Not ranked
Mercury 2.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-6 Sol
Not ranked
Mercury 2.5
77.7
#56/124
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-6 Sol
Not ranked
Mercury 2.5
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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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

GPT-6 Sol
$0.007
Fits in one request
Mercury 2.5
$0.00012
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

GPT-6 Sol
$0.13
Fits in one request
Mercury 2.5
$0.00245
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

GPT-6 Sol
$0.18
Fits in one request
Mercury 2.5
$0.0031
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.

Provider availability

GPT-6 Sol

Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex

OpenAI GPT-6 Sol and Luna launch

Mercury 2.5

Not sourced

Reasoning profile

GPT-6 Sol

Reasoning

Mercury 2.5

Reasoning

Weight access

GPT-6 Sol

Proprietary

Mercury 2.5

Proprietary

License

GPT-6 Sol

Proprietary

Mercury 2.5

Proprietary

Release date

GPT-6 Sol

2026-09-16

Mercury 2.5

2026-09-08

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.13 vs $0.00245. Cache-heavy agent loop: $0.18 vs $0.0031.
Context tradeoff
GPT-6 Sol has the larger documented window (1.05M).

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 evidence16 rows

Agentic

  • Agents' Last Exam

    GPT-6 Sol56.4%
    Source
    Mercury 2.5—

    Not directly comparable

  • AutomationBench

    GPT-6 Sol33.2%
    Source
    Mercury 2.5—

    Not directly comparable

  • OSWorld 2.0

    GPT-6 Sol60.5%
    Source
    Mercury 2.5—

    Not directly comparable

  • ExploitGym

    GPT-6 Sol22.1%
    Source
    Mercury 2.5—

    Not directly comparable

  • τ³-bench results

    GPT-6 Sol—
    Mercury 2.596.0%
    Source

    Not directly comparable

  • DeepSearchQA

    GPT-6 Sol—
    Mercury 2.534.0%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-6 Sol—
    Mercury 2.534.1%
    Source

    Not directly comparable

Coding

  • DeepSWE

    GPT-6 Sol68.8%
    Source
    Mercury 2.5—

    Not directly comparable

  • SciCode

    GPT-6 Sol—
    Mercury 2.538%
    Source

    Not directly comparable

Knowledge

  • HealthBench (raw)

    GPT-6 Sol47.1%
    Source
    Mercury 2.5—

    Not directly comparable

  • HealthBench (length-adjusted)

    GPT-6 Sol53.2%
    Source
    Mercury 2.5—

    Not directly comparable

  • HealthBench Professional

    GPT-6 Sol60.8%
    Source
    Mercury 2.5—

    Not directly comparable

  • HealthBench Professional (raw)

    GPT-6 Sol59.5%
    Source
    Mercury 2.5—

    Not directly comparable

  • HealthBench Hard

    GPT-6 Sol30.1%
    Source
    Mercury 2.5—

    Not directly comparable

  • GPQA-D

    GPT-6 Sol—
    Mercury 2.579.0%
    Source

    Not directly comparable

Instruction following

  • IFBench

    GPT-6 Sol—
    Mercury 2.577%
    Source

    Not directly comparable

Questions

Which is better, GPT-6 Sol or Mercury 2.5?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-6 Sol or Mercury 2.5?

GPT-6 Sol scores higher for coding on the public lane, 74.3 to 41.8. GPT-6 Sol and Mercury 2.5 are 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, GPT-6 Sol or Mercury 2.5?

GPT-6 Sol scores higher for agentic tasks on the public lane, 69.7 to 37.6. GPT-6 Sol and Mercury 2.5 are 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, GPT-6 Sol or Mercury 2.5?

For the stated presets, chat costs $0.007 on GPT-6 Sol and $0.00012 on Mercury 2.5; repository review costs $0.13 and $0.00245; the cache-heavy agent loop costs $0.18 and $0.0031. Costs use the listed standard API rates.

Which has the larger context window, GPT-6 Sol or Mercury 2.5?

GPT-6 Sol has the larger documented context window: 1.05M, compared with 260K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 22, 2026

Watch GPT-6 Sol vs Mercury 2.5

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

Read a sample issue

Join 2,000+ readers.