Model comparison
Claude Haiku 4.5 vs GPT-5.4
Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Haiku 4.5 #77 (Estimated); GPT-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Haiku 4.5 and GPT-5.4 share 4 comparable benchmark results. 2 of 8 categories are comparable. 1 result is unique to Claude Haiku 4.5; 48 to GPT-5.4.
Updated July 20, 2026- Shared results
- 4
- Claude Haiku 4.5 only
- 1
- GPT-5.4 only
- 48
- Comparable categories
- 2 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if coding is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 56.58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in mathematics, where it averages 42.5 against 4.9. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 5.903% to 47.600%. Claude Haiku 4.5 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $1.00 input / $5.00 output per 1M tokens for Claude Haiku 4.5. That is roughly 3.0x on output cost alone. GPT-5.4 is the reasoning model in the pair, while Claude Haiku 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.4 gives you the larger context window at 1.05M, compared with 200K for Claude Haiku 4.5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Haiku 4.5 | Δ | GPT-5.4 |
|---|---|---|---|
| Math | Claude Haiku 4.54.9 | Margin→ 37.6 | GPT-5.442.5 |
| Coding | Claude Haiku 4.573.3 | Margin← 15.6 | GPT-5.457.7 |
| Agentic | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.477.2 |
| Knowledge | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.457.6 |
| Multimodal | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.473.2 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 5.903%B 47.600%Winner: GPT-5.4Δ 41.7FrontierMath v2 (Tiers 1-3): Claude Haiku 4.5 scored 5.903%; GPT-5.4 scored 47.600%. GPT-5.4 wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 2.083%B 27.100%Winner: GPT-5.4Δ 25FrontierMath v2 (Tier 4): Claude Haiku 4.5 scored 2.083%; GPT-5.4 scored 27.100%. GPT-5.4 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Haiku 4.5 | GPT-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Haiku 4.5$1 input / $5 output | GPT-5.4$2.5 input / $15 output | Claude Haiku 4.5 has the lower combined listed price. |
| Generation speedtokens per second | Claude Haiku 4.5Not available | GPT-5.474 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Haiku 4.5Not available | GPT-5.4151.79 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Haiku 4.5200K | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.4 | Result |
|---|---|---|---|
| JobBenchSource | 16.0% | 38.9% | GPT-5.4 leads |
| Terminal-Bench 2.0Source | — | 75.1% | Not comparable |
| CyberGymSource | — | 79.0% | Not comparable |
| BrowseCompSource | — | 82.7% | Not comparable |
| OSWorld-VerifiedSource | — | 75% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| τ²-bench resultsSource | — | 87.1% | Not comparable |
| Claw-EvalSource | — | 60.3% | Not comparable |
| DeepSearchQASource | — | 73.6% | Not comparable |
| AA Agentic IndexSource | — | 41.1% | Not comparable |
| APEX-Agents-AASource | — | 33.3% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| Gert LabsSource | — | 64.89% | Not comparable |
| ResearchClawBenchSource | — | 15.3% | Not comparable |
| ExploitGymSource | — | 6.0% | Not comparable |
CodingClaude Haiku 4.5 wins7 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.4 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.3% | — | Not comparable |
| LiveCodeBench ProSource | — | 87.5% | Not comparable |
| SWE-bench ProSource | — | 57.7% | Not comparable |
| React Native EvalsSource | — | 85.3% | Not comparable |
| Vibe Code BenchSource | — | 67.42% | Not comparable |
| AA Coding IndexSource | — | 71.0% | Not comparable |
| AA-SciCodeSource | — | 56.6% | Not comparable |
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.4 | Result |
|---|---|---|---|
| GPQASource | — | 92.8% | Not comparable |
| HLESource | — | 52.1% | Not comparable |
| HLE w/o toolsSource | — | 39.8% | Not comparable |
| GPQA-DSource | — | 92.8% | Not comparable |
| HealthBench HardSource | — | 40.1% | Not comparable |
| MedXpertQA (Text)Source | — | 59.6% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 51.4% | Not comparable |
| AA-GPQA DiamondSource | — | 92.0% | Not comparable |
| AA-HLESource | — | 41.6% | Not comparable |
| AA-Omniscience IndexSource | — | 5.7% | Not comparable |
| AA-Omniscience AccuracySource | — | 50.0% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 88.6% | Not comparable |
| HealthBench ProfessionalSource | — | 48.1% | Not comparable |
MathGPT-5.4 wins2 benchmarks
Multimodal11 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.4 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1154 | 1252 | GPT-5.4 leads |
| MMMU-ProSource | — | 81.2% | Not comparable |
| OfficeQA ProSource | — | 53.2% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 82.1% | Not comparable |
| CharXivSource | — | 82.8% | Not comparable |
| ERQASource | — | 65.4% | Not comparable |
| SimpleVQASource | — | 61.1% | Not comparable |
| ScreenSpot ProSource | — | 85.4% | Not comparable |
| ZeroBenchSource | — | 41.0% | Not comparable |
| MedXpertQA (MM)Source | — | 77.1% | Not comparable |
| AA-MMMU-ProSource | — | 78.4% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.4 | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 73.9% | Not comparable |
Frequently Asked Questions (3)
Which is better, Claude Haiku 4.5 or GPT-5.4?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 56.58. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 5.903% and 47.600%.
Which is better for coding, Claude Haiku 4.5 or GPT-5.4?
Claude Haiku 4.5 has the edge for coding in this comparison, averaging 73.3 versus 57.7. GPT-5.4 stays close enough that the answer can still flip depending on your workload.
Which is better for math, Claude Haiku 4.5 or GPT-5.4?
GPT-5.4 has the edge for math in this comparison, averaging 42.5 versus 4.9. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.