Claude Haiku 5.5 vs Gemini 4 Argon
Reading a 26.2K-token pull request costs $0.0524 on Gemini 4 Argon, 20× the $0.0026 it costs on Claude Haiku 5.5. Claude Haiku 5.5 is a economy model and Gemini 4 Argon a mid-range one. The benchmark cannot separate their recall: Claude Haiku 5.5 minus Gemini 4 Argon is −18 pts (95% interval −36 pts to −1 pt).
Side by side
| Figure | Claude Haiku 5.5 | Gemini 4 Argon |
|---|---|---|
| Price tier | Economy | Mid-range |
| Bugs caughtshare of known bugs | 64% | 82% (better) |
| False alarmsper clean PR | 1.4 | 1.1 (better) |
| Cost per reviewmeasured | $0.0038 (better) | $0.0527 |
| Cost per bug caught | $0.0064 (better) | $0.0706 |
| Exact linecatches on the expected lines | 82% (better) | 78% |
| Review timemean | 15s (better) | 99s |
| 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 | 1M | 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 64% | 83% | 75% | 40% | 75% | 67% | 33% | 67% | 100% | 39% | 67% | 67% | 50% | 0% |
| Gemini 4 Argon | 82% | 83% | 50% | 83% | 75% | 89% | 67% | 100% | 100% | 83% | 100% | 100% | 100% | 0% |
Of the 42 known bugs both were scored on, both caught 24 and neither caught 2. Claude Haiku 5.5 caught 4 bugs that Gemini 4 Argon missed: 2 in Go, 1 in JavaScript and 1 in TypeScript. Gemini 4 Argon caught 12 bugs that Claude Haiku 5.5 missed: 2 in Java, 2 in JavaScript, 1 in C++, 1 in C#, 1 in Go, 1 in Kotlin, 1 in Python, 1 in Ruby, 1 in Swift and 1 in TypeScript, most of them logic bugs.
On pull requests with no known bug, Claude Haiku 5.5 raised 1.4 false alarms per review and Gemini 4 Argon 1.1. A measured review cost $0.0038 on Claude Haiku 5.5, 93% less than $0.0527 on Gemini 4 Argon.
| Pull request | Language · kind | Claude Haiku 5.5 | Gemini 4 Argon |
|---|---|---|---|
| colinhacks/zodfeat(v4): parse input containing reference cycles | TypeScript · Resource handling | 1/1 | 0/1 |
| go-gitea/giteaperf(gitdiff): optimize inline diff highlighting using cache | Go · Error handling | 1/1 | 0/1 |
| golang/gocrypto/tls: add LocalCertificate to ConnectionState | Go · Logic | 1/1 | 0/1 |
| nodejs/undicifeat: add configurable maxPayloadSize for WebSocket | JavaScript · Security | 1/1 | 0/1 |
| TanStack/queryfix(query-core): fix hydration bugs for already resolved promises | TypeScript · Logic | 0/1 | 1/1 |
| aio-libs/aiohttpkeep websocket compression state across interleaved control frames | Python · Logic | 0/1 | 1/1 |
| dotnet/orleansfix(serialization): cap codec allocations | C# · Logic | 0/1 | 1/1 |
| ggml-org/llama.cpprpc : cache and reuse compute graphs | C++ · Security | 0/1 | 1/1 |
| go-chi/chifeat: middleware.ClientIP, a replacement for middleware.RealIP | Go · Security | 0/1 | 1/1 |
| jhy/jsoupStore cached child els in Attributes, not field | Java · Concurrency | 0/2 | 1/2 |
| kotest/kotestFix DataClassEq comparator | Kotlin · Logic | 0/1 | 1/1 |
| mockito/mockitoAdd core API to enable Kotlin singleton mocking | Java · API misuse | 0/1 | 1/1 |
| pinojs/thread-streamrefactor: replace setTimeout with Atomics.waitAsync | JavaScript · Concurrency | 0/1 | 1/1 |
| pointfreeco/swift-navigationUIKit: Fix switch presented child double dismiss | Swift · Logic | 0/1 | 1/1 |
| rails/railsReimplement Action Cable redis adapter with redis-client | Ruby · Logic | 0/1 | 1/1 |
| sindresorhus/p-throttleAdd `weight` option | JavaScript · 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: Claude Haiku 5.5 and Gemini 4 Argon.