Model comparison
Claude Fable 5 vs GPT-5.4
Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Fable 5 #2 (Supported); GPT-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Fable 5 and GPT-5.4 share 20 comparable benchmark results. 3 of 8 categories are comparable. 14 results are unique to Claude Fable 5; 32 to GPT-5.4.
Updated July 23, 2026- Shared results
- 20
- Claude Fable 5 only
- 14
- GPT-5.4 only
- 32
- Comparable categories
- 3 / 8
Pick Claude Fable 5 if you want the stronger benchmark profile. GPT-5.4 only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 6 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Claude Fable 5 is clearly ahead on the BenchAlign aggregate, 83.68 to 74.24. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Fable 5's sharpest advantage is in coding, where it averages 89.2 against 57.7. The single biggest benchmark swing on the page is SWE-bench Pro, 80% to 57.7%. GPT-5.4 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $2.50 input / $15.00 output per 1M tokens for GPT-5.4. That is roughly 3.3x on output cost alone. GPT-5.4 gives you the larger context window at 1.05M, compared with 1M+ for Claude Fable 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 Fable 5 | Δ | GPT-5.4 |
|---|---|---|---|
| Coding | Claude Fable 589.2 | Margin← 31.5 | GPT-5.457.7 |
| Multimodal | Claude Fable 557.9 | Margin→ 15.3 | GPT-5.473.2 |
| Agentic | Claude Fable 584.6 | Margin← 7.4 | GPT-5.477.2 |
| Knowledge | Claude Fable 5Not measured | MarginNo overlap | GPT-5.457.6 |
| Math | Claude Fable 5Not measured | MarginNo overlap | GPT-5.442.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Pro
CodingA 80%B 57.7%Winner: Claude Fable 5Δ 22.3SWE-bench Pro: Claude Fable 5 scored 80%; GPT-5.4 scored 57.7%. Claude Fable 5 wins this benchmark. - Source ↗
OSWorld-Verified
AgenticA 85%B 75%Winner: Claude Fable 5Δ 10OSWorld-Verified: Claude Fable 5 scored 85%; GPT-5.4 scored 75%. Claude Fable 5 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 84.3%B 75.1%Winner: Claude Fable 5Δ 9.2Terminal-Bench 2.0: Claude Fable 5 scored 84.3%; GPT-5.4 scored 75.1%. Claude Fable 5 wins this benchmark. - Source ↗
OfficeQA Pro
MultimodalA 57.9%B 53.2%Winner: Claude Fable 5Δ 4.7OfficeQA Pro: Claude Fable 5 scored 57.9%; GPT-5.4 scored 53.2%. Claude Fable 5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Fable 5 | GPT-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Fable 5$10 input / $50 output | GPT-5.4$2.5 input / $15 output | GPT-5.4 has the lower combined listed price. |
| Generation speedtokens per second | Claude Fable 5Not available | GPT-5.474 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Fable 5Not available | GPT-5.4151.79 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Fable 51M+ | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticClaude Fable 5 wins24 benchmarks
| Benchmark | Claude Fable 5 | GPT-5.4 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 84.3% | 75.1% | Claude Fable 5 leads |
| OSWorld-VerifiedSource | 85% | 75% | Claude Fable 5 leads |
| GDPval-AASource | 1748 | 1395 | Claude Fable 5 leads |
| AA Agentic IndexSource | 52.8% | 41.1% | Claude Fable 5 leads |
| τ²-bench resultsSource | 98.5% | 87.1% | Claude Fable 5 leads |
| GDPval-AASource | 62.4% | 44.7% | Claude Fable 5 leads |
| AA BriefcaseSource | 1574 | — | Not comparable |
| AA AutomationBenchSource | 48.6% | — | Not comparable |
| AA EnterpriseOps-GymSource | 51.1% | — | Not comparable |
| AA Harvey LABSource | 93.6% | — | Not comparable |
| AA Tau3 BankingSource | 26.8% | — | Not comparable |
| terminalBenchHardSource | 62.9% | — | Not comparable |
| aaTerminalBench21Source | 84.6% | — | Not comparable |
| CyberGymSource | — | 79.0% | Not comparable |
| BrowseCompSource | — | 82.7% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| Claw-EvalSource | — | 60.3% | Not comparable |
| DeepSearchQASource | — | 73.6% | Not comparable |
| APEX-Agents-AASource | — | 33.3% | Not comparable |
| Gert LabsSource | — | 64.89% | Not comparable |
| ResearchClawBenchSource | — | 15.3% | Not comparable |
| JobBenchSource | — | 38.9% | Not comparable |
| ExploitGymSource | — | 6.0% | Not comparable |
CodingClaude Fable 5 wins12 benchmarks
| Benchmark | Claude Fable 5 | GPT-5.4 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 95% | — | Not comparable |
| SWE-bench ProSource | 80% | 57.7% | Claude Fable 5 leads |
| FrontierCode 1.1 MainSource | 53.5% | — | Not comparable |
| Terminal-Bench 2.0Source | 84.3% | — | Not comparable |
| cursorBench31Source | 70.6% | — | Not comparable |
| cursorBench32Source | 70.5% | — | Not comparable |
| VulcanBench v3Source | 87.0% | — | Not comparable |
| AA Coding IndexSource | 76.5% | 71.0% | Claude Fable 5 leads |
| AA-SciCodeSource | 60.2% | 56.6% | Claude Fable 5 leads |
| LiveCodeBench ProSource | — | 87.5% | Not comparable |
| React Native EvalsSource | — | 85.3% | Not comparable |
| Vibe Code BenchSource | — | 67.42% | Not comparable |
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | Claude Fable 5 | GPT-5.4 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 59.9% | 51.4% | Claude Fable 5 leads |
| AA-GPQA DiamondSource | 92.6% | 92.0% | Claude Fable 5 leads |
| AA-HLESource | 53.3% | 41.6% | Claude Fable 5 leads |
| AA-Omniscience IndexSource | 40.2% | 5.7% | Claude Fable 5 leads |
| AA-Omniscience AccuracySource | 61.4% | 50.0% | Claude Fable 5 leads |
| AA-Omniscience Hallucination RateSource | 54.9% | 88.6% | Claude Fable 5 leads |
| 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 |
| HealthBench ProfessionalSource | — | 48.1% | Not comparable |
Math2 benchmarks
MultimodalGPT-5.4 wins12 benchmarks
| Benchmark | Claude Fable 5 | GPT-5.4 | Result |
|---|---|---|---|
| Blueprint-Bench 2Source | 38.6% | — | Not comparable |
| OfficeQA ProSource | 57.9% | 53.2% | Claude Fable 5 leads |
| Design Arena WebsiteSource | 1332 | 1250 | Claude Fable 5 leads |
| MMMU-ProSource | — | 81.2% | 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 Fable 5 | GPT-5.4 | Result |
|---|---|---|---|
| AA-IFBenchSource | 63.5% | 73.9% | GPT-5.4 leads |
Frequently Asked Questions (4)
Which is better, Claude Fable 5 or GPT-5.4?
Claude Fable 5 is ahead on BenchLM's BenchAlign leaderboard, 83.68 to 74.24. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 80% and 57.7%.
Which is better for coding, Claude Fable 5 or GPT-5.4?
Claude Fable 5 has the edge for coding in this comparison, averaging 89.2 versus 57.7. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Fable 5 or GPT-5.4?
Claude Fable 5 has the edge for agentic tasks in this comparison, averaging 84.6 versus 77.2. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Fable 5 or GPT-5.4?
GPT-5.4 has the edge for multimodal and grounded tasks in this comparison, averaging 73.2 versus 57.9. Inside this category, Design Arena Website 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.