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 Luna vs GPT-6 Sol

Decision reading

GPT-6 Sol has the higher public score estimate, 80.45 versus 62.33, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 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 Luna

OpenAI

62.33/100

Estimated · Public rank #56

90% interval 45.7–73.8

OpenAI logo
Model B
GPT-6 Sol

OpenAI

80.45/100

Estimated · Public rank #7

90% interval 51.1–92.0

Updated September 22, 2026. Rank says GPT-6 Sol is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty. This is a same-family comparison, so migration details appear when the source data supports them.

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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-6 Luna

    GPT-6 Luna 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

    GPT-6 Luna

    GPT-6 Luna 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

    GPT-6 Luna

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

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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.

66.6GPT-6 Luna74.3GPT-6 Sol

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
7
GPT-6 Luna only
0
GPT-6 Sol only
3
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 Luna
56.7
Estimated · #35/157
GPT-6 Sol
69.7
Estimated · #7/157
Basis
BenchAlign lane · 1 vs 4 public rows
Reading
Directional only

Coding

Directional only
GPT-6 Luna
66.6
Estimated · #11/159
GPT-6 Sol
74.3
Estimated · #6/159
Basis
BenchAlign lane · 1 vs 1 public rows
Reading
Directional only

Knowledge

Directional only
GPT-6 Luna
63.6
Estimated · #29/189
GPT-6 Sol
80.2
Estimated · #6/189
Basis
BenchAlign lane · 5 vs 5 public rows
Reading
Directional only

Reasoning

Not comparable
GPT-6 Luna
78.3
Unranked · 2 rankable rows
GPT-6 Sol
78.5
#5/17
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GPT-6 Luna
71.3
Unranked · 1 rankable row
GPT-6 Sol
82.8
Unranked · 1 rankable row
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

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

Instruction following

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

Math

Not comparable
GPT-6 Luna
Not ranked
GPT-6 Sol
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 Luna
$0.00035
Fits in one request
GPT-6 Sol
$0.007
Fits in one request

GPT-6 Luna has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-6 Luna
$0.0065
Fits in one request
GPT-6 Sol
$0.13
Fits in one request

GPT-6 Luna 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 Luna
$0.009
Fits in one request
GPT-6 Sol
$0.18
Fits in one request

GPT-6 Luna 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

GPT-6 Luna

Reasoning

GPT-6 Sol

Reasoning

Weight access

GPT-6 Luna

Proprietary

GPT-6 Sol

Proprietary

License

GPT-6 Luna

Proprietary

GPT-6 Sol

Proprietary

Release date

GPT-6 Luna

2026-09-16

GPT-6 Sol

2026-09-16

If you are choosing between sibling variants
Deployment change
Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
GPT-6 Sol has the higher public score estimate, 80.45 versus 62.33, but the 90% score intervals overlap.
Workload cost
Repository review: $0.0065 vs $0.13. Cache-heavy agent loop: $0.009 vs $0.18.
Context tradeoff
Both models list 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 evidence10 rows

Agentic

  • ExploitGym

    Shared source
    GPT-6 Luna11.6%
    GPT-6 Sol22.1%

    GPT-6 Sol leads this result

  • Agents' Last Exam

    GPT-6 Luna—
    GPT-6 Sol56.4%
    Source

    Not directly comparable

  • AutomationBench

    GPT-6 Luna—
    GPT-6 Sol33.2%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-6 Luna—
    GPT-6 Sol60.5%
    Source

    Not directly comparable

Coding

  • DeepSWE

    Shared source
    GPT-6 Luna66.6%
    GPT-6 Sol68.8%

    GPT-6 Sol leads this result

Knowledge

  • HealthBench (raw)

    Shared source
    GPT-6 Luna50.0%
    GPT-6 Sol47.1%

    GPT-6 Luna leads this result

  • HealthBench (length-adjusted)

    Shared source
    GPT-6 Luna54.5%
    GPT-6 Sol53.2%

    GPT-6 Luna leads this result

  • HealthBench Professional

    Shared source
    GPT-6 Luna60.8%
    GPT-6 Sol60.8%

    Tie

  • HealthBench Professional (raw)

    Shared source
    GPT-6 Luna61.2%
    GPT-6 Sol59.5%

    GPT-6 Luna leads this result

  • HealthBench Hard

    Shared source
    GPT-6 Luna31.4%
    GPT-6 Sol30.1%

    GPT-6 Luna leads this result

Questions

Which is better, GPT-6 Luna or GPT-6 Sol?

GPT-6 Sol has the higher public score estimate, 80.45 versus 62.33, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

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

GPT-6 Sol scores higher for coding on the public lane, 74.3 to 66.6. GPT-6 Luna and GPT-6 Sol 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 Luna or GPT-6 Sol?

GPT-6 Sol scores higher for agentic tasks on the public lane, 69.7 to 56.7. GPT-6 Luna and GPT-6 Sol 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 Luna or GPT-6 Sol?

For the stated presets, chat costs $0.00035 on GPT-6 Luna and $0.007 on GPT-6 Sol; repository review costs $0.0065 and $0.13; the cache-heavy agent loop costs $0.009 and $0.18. Costs use the listed standard API rates.

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

Both models list the same context window, 1.05M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 22, 2026

Watch GPT-6 Luna vs GPT-6 Sol

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

Read a sample issue

Join 2,000+ readers.