Gemini 3.1 Pro vs GPT-OSS 120B (Workers AI)
Reading a 26.2K-token pull request costs $0.0524 on Gemini 3.1 Pro, 5.7× the $0.0092 it costs on GPT-OSS 120B (Workers AI). Gemini 3.1 Pro is a mid-range model and GPT-OSS 120B (Workers AI) a economy one. In the benchmark Gemini 3.1 Pro caught 27 percentage points more of the known defects than GPT-OSS 120B (Workers AI) (95% interval +16 pts to +38 pts, a − b).
Side by side
| Figure | Gemini 3.1 Pro | GPT-OSS 120B (Workers AI) |
|---|---|---|
| Price tier | Mid-range | Economy |
| Bugs caughtshare of known bugs | 67% (better) | 40% |
| False alarmsper clean PR | 0.8 (better) | 2.5 |
| Cost per reviewmeasured | $0.2499 | $0.0075 (better) |
| Cost per bug caught | $0.4134 | $0.0189 (better) |
| Exact linecatches on the expected lines | 89% (better) | 49% |
| Review timemean | 349s | 55s (better) |
| Typical review calllist price | $0.0814 | $0.011 (better) |
| Input / 1M tokens | $2.00 | $0.35 (better) |
| Output / 1M tokens | $12.00 | $0.75 (better) |
| Context window | 1M | 128K |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.1 Pro | 67% | 67% | 38% | 78% | 88% | 56% | 33% | 67% | 67% | 67% | 100% | 100% | 50% | 50% |
| GPT-OSS 120B (Workers AI) | 40% | 42% | 13% | 46% | 71% | 41% | 11% | 44% | 33% | 78% | 33% | 44% | 33% | 0% |
Of the 42 known bugs both were scored on, both caught 27 and neither caught 8. Gemini 3.1 Pro caught 5 bugs that GPT-OSS 120B (Workers AI) missed: 1 in C, 1 in Go, 1 in Ruby, 1 in Rust and 1 in Swift. GPT-OSS 120B (Workers AI) caught 2 bugs that Gemini 3.1 Pro missed: 1 in Go and 1 in TypeScript.
On pull requests with no known bug, Gemini 3.1 Pro raised 0.8 false alarms per review and GPT-OSS 120B (Workers AI) 2.5. A measured review cost $0.2499 on Gemini 3.1 Pro, 33× the cost of $0.0075 on GPT-OSS 120B (Workers AI).
| Pull request | Language · kind | Gemini 3.1 Pro | GPT-OSS 120B (Workers AI) |
|---|---|---|---|
| groue/GRDB.swiftDatabaseQueue and DatabaseSnapshot reads can access task locals | Swift · Concurrency | 1/1 | 0/3 |
| rails/railsReimplement Action Cable redis adapter with redis-client | Ruby · Logic | 1/1 | 0/3 |
| traefik/traefikAdd the option to define custom cipher suites for backend serversTransport | Go · API misuse | 1/1 | 0/6 |
| 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 | 1/2 | 0/3 |
| nushell/nushellreorganize nushell configuration | Rust · Error handling | 1/2 | 0/6 |
| TanStack/queryfix(query-core): fix hydration bugs for already resolved promises | TypeScript · Logic | 0/1 | 1/6 |
| go-gitea/giteaperf(gitdiff): optimize inline diff highlighting using cache | Go · Error handling | 0/1 | 1/3 |
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: Gemini 3.1 Pro and GPT-OSS 120B (Workers AI).