Across 21 comparable benchmarks, GPT-5.1 has better reported results on 20 and worse on 1. 2 further shared results are listed below, each with the reason it is not counted.
Moderate evidence21 of 23 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | GPT-5.1 | Haiku 4.5 |
|---|---|---|
| Context window | 400K tokens | 200K tokens |
| Input / 1M | $1.25 | $1.00 |
| Output / 1M | $10.00 | $5.00 |
| Blended (4:1) | $2.19 | $1.15 |
| Status | Deprecated | Available |
| Released | November 12, 2025 | October 15, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 15 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
GPT-5.1 ahead on 5 of 5 counted
GPT-5.1 ahead on 1 of 1 counted
GPT-5.1 ahead on 2 of 3 counted
GPT-5.1 ahead on 3 of 3 counted
GPT-5.1 ahead on 1 of 1 counted
GPT-5.1 ahead on 2 of 2 counted
GPT-5.1 ahead on 2 of 2 counted
No shared comparable results for Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT-5.1 relative to Haiku 4.5. Reading the results
| Benchmark | GPT-5.1 | Haiku 4.5 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 86.8Thinking High · no tools | 62.0≠Extended · no tools | 1.40×#19 vs #69 of 113 |
| SWE-Bench Pro - PublicRepository Engineering · Accuracy | 50.8Thinking High · no tools | 39.5≠Extended · tools | +11.3 pts#48 vs #63 of 66 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 76.3Thinking High · no tools | 73.3≠Thinking · tools · 128K | +3.0 pts#32 vs #47 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 45.5Thinking High · tools | 27.3≠Normal · tools | +18.2 pts#20 vs #74 of 157 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 24.6Thinking High · tools | 11.4≠Thinking · tools | +13.2 pts#82 vs #102 of 121 |
| ARC-AGI-1Abstract Generalization · Score (%) | 72.8Thinking High · no tools | 47.7≠Extended · no tools | +25.2 pts#51 vs #67 of 87 |
| ARC-AGI-2Abstract Generalization · Score (% solved); cost per task (USD)Not counted · Speed and cost telemetry is reported, not scored | 17.6Thinking High · no tools | 4.5≠Extended · no tools | 3.92×#55 vs #70 of 80 |
| Vending-Bench 2Logical Planning · Money Balance (USD)Not counted · Speed and cost telemetry is reported, not scored | 1473Unspecified Reasoning · tools | 459Unspecified Reasoning · tools | 3.21×#51 vs #58 of 64 |
| AIME2025Mathematics · Accuracy | 94.2Thinking High · tools | 96.3≠Thinking · tools · 128K | −2.1 pts#26 vs #18 of 86 |
| FrontierMathMathematics · Accuracy | 26.7Thinking High · tools | 4.1≠Normal · no tools | +22.6 pts#12 vs #32 of 48 |
| FrontierMath - Tier 4Mathematics · Accuracy | 12.5Thinking High · no tools | 2.1≠Thinking · no tools · 32K | +10.4 pts#13 vs #31 of 50 |
| GPQA DiamondScientific Reasoning · Accuracy | 88.1Thinking · no tools | 73.3≠Extended · no tools | +14.8 pts#65 vs #126 of 200 |
| MedCodeClinical Workflows · Accuracy (%) | 52.7Thinking High · tools | 32.7≠Thinking · tools | +20.0 pts#13 vs #81 of 97 |
| MedScribeClinical Workflows · Rubric pass rate (%) | 88.1Thinking High · tools | 85.2≠Thinking · tools | +2.9 pts#14 vs #30 of 99 |
| MCP-AtlasTool Orchestration · Pass rate / claim coverage | 50.1Thinking High · tools | 40.2≠Normal · tools | +9.9 pts#53 vs #55 of 55 |
| MMMUVisual Understanding · Accuracy | 85.4Thinking High · no tools | 73.2≠Thinking · no tools · 128K | +12.2 pts#1 vs #27 of 62 |
| MMMU-ProVisual Understanding · Accuracy | 79.0Thinking · no tools | 58.6Thinking · no tools | +20.4 pts#38 vs #109 of 136 |
| SAGEService Workflows · Accuracy (%) | 43.2Thinking High · tools | 31.8≠Thinking · tools | +11.4 pts#51 vs #71 of 82 |
| τ³-BankingService Workflows · Score | 15.9Thinking High · tools | 9.3≠Thinking · tools | 1.71×#69 vs #95 of 120 |
| HLEKnowledge Exams · Accuracy | 42.7Thinking High · tools + web | 9.7≠Extended · no tools | +33.0 pts#74 vs #129 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 87.0Thinking High · no tools | 80.0≠Normal · no tools | +7.0 pts#16 vs #62 of 153 |
| ECICapability Indices · ECI score (capability index, higher is better) | 150Reported best | 142Reported best | 1.05×#51 vs #90 of 168 |
| LiveBenchCross-capability Suites · Accuracy | 72.0Thinking High · no tools | 61.3≠Thinking · no tools · 64K | +10.7 pts#50 vs #82 of 106 |
Algorithmic Coding · Pass @K
Repository Engineering · Accuracy
Repository Engineering · Accuracy
Agentic Development · Accuracy
Code Generation & Editing · Pass rate (%)
Abstract Generalization · Score (%)
Abstract Generalization · Score (% solved); cost per task (USD)
Not counted · Speed and cost telemetry is reported, not scored
Logical Planning · Money Balance (USD)
Not counted · Speed and cost telemetry is reported, not scored
Mathematics · Accuracy
Mathematics · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Accuracy
Clinical Workflows · Accuracy (%)
Clinical Workflows · Rubric pass rate (%)
Tool Orchestration · Pass rate / claim coverage
Service Workflows · Accuracy (%)
Service Workflows · Score
A dash means no result is available.
| Benchmark | GPT-5.1 | Haiku 4.5 |
|---|---|---|
| CritPt | 4.9 | — |
| IMO-ProofBench Advanced | 7.1 | — |
| MathArena Apex | 1.0 | — |
| SciCode | — | 42.2 |
| Code Migration | — | 7.5 |
| GSO | 13.7 | — |
| IC SWE-Lancer (Diamond) | 69.7 | — |
| SWE-Bench Pro V2 Hard | — | 25.5 |
| Terminal Bench 2.0 | 47.6 | — |
| Terminal-Bench 1.0 | — | 41.8 |
| WeirdML v2 | 60.8 | — |
| Claw Bench | — | 89.4 |
| OSWorld 2.1 | — | 15.7 |
| Pinch Bench | — | 82.0 |
| PinchBench v2 | — | 67.7 |
| ExploitBench | — | 13.7 |
| AA Intelligence Index v5.0.1 | — | 7.4 |
| LiveBench 2.0 | — | 46.0 |
| Text Arena (Coding) | 1387 | — |
| Vals Index | — | 22.9 |
| IF Bench | — | 54.3 |
| Context Arena | — | 36.3 |
| GDP.pdf | — | 3.8 |
| VPCT | 58.7 | — |
| AA-AnalystAgent | — | 15.0 |
| AutomationBench | — | 0.46 |
| EMB (Excel Modeling) | — | 22.7 |
| Finance Agent v2 | — | 31.0 |
| Harvey Lab-AA | — | 61.0 |
| Harvey's Legal Agent Benchmark | — | 0.83 |
| Legal Research Bench | — | 10.6 |
| Public Benefits Bench v1.1 | — | 54.3 |
| τ²-Bench | — | 33.0 |
| BALROG | — | 31.2 |
| SimpleBench | 53.2 | — |
| BrowseComp | 50.8 | — |
| GAIA | — | 56.4 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
GPT-5.1 costs90%morethan Haiku 4.5 per million tokens.Using standard rates at this token mix.
GPT-5.1: Standard pricing. OpenAI official pricing (developers.openai.com/api/docs/pricing) verified 2026-11-13; standard tier; Deprecated; shutdown 2027-04-01 (replacement: gpt-6-sol)
Haiku 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13
| Price / 1M tokens | GPT-5.1 | Haiku 4.5 | Ratio |
|---|---|---|---|
| Input | $1.25 | $1.00 | 1.25× |
| Output | $10.00 | $5.00 | 2.00× |
| Cached input | $0.125 | $0.10 | 1.25× |
| Cache write | — | — | — |
| Blended | $2.19 | $1.15 | 1.90× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
GPT-5.1 relative to Haiku 4.5
No matching recorded settings for a cost summary.
Summary: 0 of 1 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ or are not recorded; interpret the comparison with care.
GPT-5.1
Haiku 4.5
| Benchmark | GPT-5.1 | Haiku 4.5 |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| AutomationBench | Not reported | $0.07 / task Average · Pass Rate: 0.46 Reported best (effort unspecified) · zapier-private-heldout |
| LiveBench 2.0 | Not reported | $0.934 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 46.0 Max (task-specific tools) |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| Public Benefits Bench v1.1 | Not reported | $0.2245 / task Average · Criterion pass rate (%): 54.3 Unspecified Reasoning (With Tools) |
| SAGE | Not reported | |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | GPT-5.1 | Haiku 4.5 |
|---|---|---|
| Availability | Deprecated | Available |
| Provider | OpenAI | Anthropic |
| Model type | Reasoning model | Multimodal model |
| First release | November 12, 2025 | October 15, 2025 |
| Context window | 400K tokens | 200K tokens |
| Max output | 128K tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used GPT-5.1 or Haiku 4.5? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.