GPT-6 Luna vs GPT-6.1 Sol
Reading a 26.2K-token pull request costs $0.0524 on GPT-6.1 Sol, 20× the $0.0026 it costs on GPT-6 Luna. GPT-6 Luna is a economy model and GPT-6.1 Sol a mid-range one. The benchmark cannot separate their recall: GPT-6 Luna minus GPT-6.1 Sol is −22 pts (95% interval −36 pts to −8 pts).
Side by side
| Figure | GPT-6 Luna | GPT-6.1 Sol |
|---|---|---|
| Price tier | Economy | Mid-range |
| Bugs caughtshare of known bugs | 67% | 89% (better) |
| False alarmsper clean PR | 0.7 (better) | 0.9 |
| Cost per reviewmeasured | $0.0028 (better) | $0.0401 |
| Cost per bug caught | $0.0046 (better) | $0.0514 |
| Exact linecatches on the expected lines | 97% (better) | 95% |
| Review timemean | 29s | 28s (better) |
| Typical review calllist price | $0.0038 (better) | $0.0766 |
| Input / 1M tokens | $0.10 (better) | $2.00 |
| Output / 1M tokens | $0.50 (better) | $10.00 |
| Context window | 1.1M | 1.1M |
Head to head
The known bugs both were scored on, by who caught each in at least one run.
By language
| Model | All | TypeScript6 bugs | Go4 bugs | Java4 bugs | Rust4 bugs | C#3 bugs | JavaScript3 bugs | Kotlin3 bugs | PHP3 bugs | Python3 bugs | Ruby3 bugs | Swift3 bugs | C++2 bugs | C1 bug |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-6 Luna | 67% | 83% | 25% | 65% | 75% | 56% | 67% | 67% | 67% | 100% | 67% | 100% | 50% | 0% |
| GPT-6.1 Sol | 89% | 83% | 75% | 70% | 100% | 89% | 100% | 100% | 100% | 100% | 100% | 100% | 50% | 100% |
Of the 42 known bugs both were scored on, both caught 28 and neither caught 3. GPT-6 Luna caught one bug that GPT-6.1 Sol missed: 1 in TypeScript. GPT-6.1 Sol caught 10 bugs that GPT-6 Luna missed: 2 in Go, 1 in C, 1 in C#, 1 in JavaScript, 1 in Kotlin, 1 in PHP, 1 in Ruby, 1 in Rust and 1 in TypeScript.
On pull requests with no known bug, GPT-6 Luna raised 0.7 false alarms per review and GPT-6.1 Sol 0.9. A measured review cost $0.0028 on GPT-6 Luna, 93% less than $0.0401 on GPT-6.1 Sol.
| Pull request | Language · kind | GPT-6 Luna | GPT-6.1 Sol |
|---|---|---|---|
| trpc/trpcfix(server): pass maxDurationMs timeout signal to subscription handlers | TypeScript · Concurrency | 1/1 | 0/1 |
| c-ares/c-aresEvent Thread could stall when not notified of new queries on existing connections that are in a bad state | C · Resource handling | 0/1 | 1/1 |
| dotnet/orleansfix(serialization): cap codec allocations | C# · Logic | 0/1 | 1/1 |
| golang/gocrypto/tls: add LocalCertificate to ConnectionState | Go · Logic | 0/1 | 1/1 |
| kotest/kotestFix DataClassEq comparator | Kotlin · Logic | 0/1 | 1/1 |
| nushell/nushellreorganize nushell configuration | Rust · Error handling | 0/1 | 1/1 |
| sindresorhus/p-throttleAdd `weight` option | JavaScript · Logic | 0/1 | 1/1 |
| socketry/asyncBarrier wait in completion order + `Queue#close`. | Ruby · Concurrency | 0/1 | 1/1 |
| symfony/symfony[Security] Allow multiple OIDC discovery endpoints | PHP · Security | 0/1 | 1/1 |
| traefik/traefikAdd the option to define custom cipher suites for backend serversTransport | Go · API misuse | 0/1 | 1/1 |
| withastro/astroPort Go's csrf protection | TypeScript · Logic | 0/1 | 1/1 |
Defects caught over all runs: a PR reviewed three times with one known bug shows 3/3 when it was caught every time.
Every bug each was scored on: GPT-6 Luna and GPT-6.1 Sol.