As of October 20, 2026, SpaceXAI Grok 4.5 ranks #31 of 213 models overall with 38.8 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #13 of 147. SpaceXAI Grok 4.5 costs $2.00 per million input tokens and $6.00 per million output tokens. It was released on July 8, 2026.
Its output price ranks 260 of 349 priced models, counting from the cheapest.
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
x-ai/grok-4.5 The tick on a coding bar is the median of every model measured on it. Outside coding, the place is this model's rank on that board. A board that never ran the model says so.
Measured in 6 of 6 categories. A place counts only the models measured on that board.
The index averages only the coding benchmarks that have a result; the others are skipped, never filled in. How it is weighted
Not measured on SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, SWE-bench Multilingual, SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, FrontierSWE, GSO-Bench, MirrorCode, Cybench
Not measured on Design Arena: spreadsheets, Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, TheAgentCompany, OSWorld, SpireClimb
Not measured on MysteryMechanism (Vals AI), Humanity's Last Exam, Mystery game puzzles, EBR-bench, VPCT, BIG-Bench Hard
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on CaseLaw (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Index, Public Benefits Bench (Vals AI), IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: captioning, LMArena Vision: recognizing things
Not measured on Design Arena: images, Design Arena: graphic design, Design Arena: logos, LMArena Text to Image, LMArena Image Edit
Public boards shown as published (Vals AI, Artificial Analysis, Design Arena) and kept out of the coding index. Each links to its source on the benchmark page.
| Benchmark | Result | Index weight |
|---|---|---|
| Aider polyglotCoding | Not measured | 35% |
| SWE-bench VerifiedCoding | Not measured | 30% |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | Not measured | Not in index |
| LiveBench codingCoding | 94.3% | 20% |
| LMArena WebDevCoding | 1553 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 92.9% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 89.2% | Not in index |
| AA Intelligence IndexIntelligence | 38.8 | Not in index |
| AA Coding IndexCoding | 72.4 | Not in index |
| AA Agentic IndexAgentic work | 41.2 | Not in index |
| Design Arena: websitesWeb design | 1281 | Not in index |
| Design Arena: UI componentsWeb design | 1279 | Not in index |
| Design Arena: game devWeb design | 1263 | Not in index |
| Design Arena: data vizWeb design | 1267 | Not in index |
| Design Arena: 3DWeb design | 1258 | Not in index |
| Design Arena: all code categoriesWeb design | 1276 | Not in index |
| Design Arena: SVGWeb design | 1216 | Not in index |
| Design Arena: ASCII artWeb design | 1258 | Not in index |
| Design Arena: agents building web appsAgentic work | 1217 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1249 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1219 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1249 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1229 | Not in index |
| Design Arena: agents building gamesAgentic work | 1235 | Not in index |
| Design Arena: HTML slidesAgentic work | 1204 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1232 | Not in index |
| Design Arena: spreadsheetsAgentic work | Not measured | Not in index |
| Design Arena: imagesImage generation | Not measured | Not in index |
| Design Arena: graphic designImage generation | Not measured | Not in index |
| Design Arena: logosImage generation | Not measured | Not in index |
| LiveBench reasoningReasoning | 87.2% | Not in index |
| LiveBench data analysisGeneral | 73.0% | Not in index |
| LiveBench researchAgentic work | 85.9% | Not in index |
| LiveBench browserAgentic work | 44.0% | Not in index |
| LiveBench long agenticAgentic work | 27.9% | Not in index |
| LiveBench designWeb design | 78.1% | Not in index |
| LiveCodeBench (Vals AI)Coding | 87.3% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 86.6% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 8.6% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 69.0% | Not in index |
| Code migration (Vals AI)Coding | 36.6% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | 0.8% | Not in index |
| IOI (Vals AI)Coding | 40.6% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 67.8% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | Not measured | Not in index |
| SkillsBench (Vals AI)Coding | 66.0% | Not in index |
| CyberBench (Vals AI)Coding | 71.0% | Not in index |
| Finance Agent (Vals AI)Agentic work | 48.4% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 24.9% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 38.0% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 52.9% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | Not measured | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 6.3% | Not in index |
| CUA-bench (Vals AI)Agentic work | Not measured | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | Not measured | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 61.8% | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | Not measured | Not in index |
| SAGE (Vals AI)General | 35.0% | Not in index |
| LegalBench (Vals AI)Knowledge | 86.0% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 67.4% | Not in index |
| TaxEval (Vals AI)Knowledge | 71.7% | Not in index |
| MortgageTax (Vals AI)Knowledge | 61.8% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 43.3% | Not in index |
| MedScribe (Vals AI)General | 86.9% | Not in index |
| Vals Multimodal IndexGeneral | 63.4% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 93.1% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 42.7% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | Not measured | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | Not measured | Not in index |
| SciCodeCoding | 55.0% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | Not measured | Not in index |
| IFBenchGeneral | Not measured | Not in index |
| Long context reasoning (AA-LCR)General | 79.3% | Not in index |
| τ²-Bench TelecomAgentic work | Not measured | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | 53.8% | Not in index |
| FrontierCodeCoding | 42.4% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 46.4% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 56.2% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | Not measured | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | 23.4% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 93.4% | Not in index |
| ARC-AGIReasoning | 87.2% | Not in index |
| ARC-AGI-2Reasoning | 52.6% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 70.0% | Not in index |
| Chess puzzlesReasoning | 35.0% | Not in index |
| Mystery game puzzlesReasoning | Not measured | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 97.8% | Not in index |
| FrontierMath, tiers 1 to 3Math | 57.2% | Not in index |
| FrontierMath, tier 4Math | 24.4% | Not in index |
| ProofBenchMath | 31.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 48.3% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 96.5% | Not in index |
| LMCAGeneral | 45.2% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | 74.4% | Not in index |
| Furniture assemblyGeneral | 22.5% | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | Not measured | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | Not measured | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | Not measured | Not in index |
| BIG-Bench HardReasoning | Not measured | Not in index |
| AI2 Reasoning ChallengeKnowledge | Not measured | Not in index |
| HellaSwagGeneral | Not measured | Not in index |
| WinoGrandeGeneral | Not measured | Not in index |
| PIQAGeneral | Not measured | Not in index |
| CL-bench LifeGeneral | Not measured | Not in index |
| ALE-BenchCoding | 1309.3 | Not in index |
| Vending-Bench 2Agentic work | $3,887 | Not in index |
| Epoch Capabilities IndexIntelligence | 153.9 | Not in index |
| LMArena TextGeneral | 1448 | Not in index |
| LMArena Text: codingCoding | 1474 | Not in index |
| LMArena Text: hard promptsReasoning | 1462 | Not in index |
| LMArena Text: mathMath | 1459 | Not in index |
| LMArena Text: instruction followingGeneral | 1446 | Not in index |
| LMArena Text: creative writingGeneral | 1442 | Not in index |
| LMArena VisionGeneral | 1287 | Not in index |
| LMArena Text: EnglishGeneral | 1453 | Not in index |
| LMArena Text: non-EnglishGeneral | 1440 | Not in index |
| LMArena Text: ChineseGeneral | 1495 | Not in index |
| LMArena Text: GermanGeneral | 1448 | Not in index |
| LMArena Text: JapaneseGeneral | 1431 | Not in index |
| LMArena Text: KoreanGeneral | 1406 | Not in index |
| LMArena Text: FrenchGeneral | 1457 | Not in index |
| LMArena Text: SpanishGeneral | 1451 | Not in index |
| LMArena Text: RussianGeneral | 1449 | Not in index |
| LMArena Text: PolishGeneral | 1433 | Not in index |
| LMArena Text: multi-turnGeneral | 1456 | Not in index |
| LMArena Text: longer queriesGeneral | 1463 | Not in index |
| LMArena Text: expertReasoning | 1466 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1464 | Not in index |
| LMArena Text: software and ITCoding | 1471 | Not in index |
| LMArena Text: mathematical workMath | 1481 | Not in index |
| LMArena Text: scienceKnowledge | 1465 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1441 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1463 | Not in index |
| LMArena Text: business and financeKnowledge | 1441 | Not in index |
| LMArena Text: writing and languageGeneral | 1445 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1434 | Not in index |
| LMArena WebDev: ReactCoding | 1556 | Not in index |
| LMArena WebDev: HTMLCoding | 1567 | Not in index |
| LMArena WebDev: from an imageCoding | 1562 | Not in index |
| LMArena Vision: EnglishGeneral | 1285 | Not in index |
| LMArena Vision: ChineseGeneral | 1345 | Not in index |
| LMArena Vision: reading textGeneral | 1293 | Not in index |
| LMArena Vision: diagramsReasoning | 1304 | Not in index |
| LMArena Vision: homeworkReasoning | 1295 | Not in index |
| LMArena Vision: humorGeneral | 1276 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1293 | Not in index |
| LMArena SearchAgentic work | 1216 | Not in index |
| LMArena DocumentGeneral | 1452 | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
A list price says what a token costs. The cost per solved task says what a working answer costs, which is the number that decides.
Beside a result, many boards publish what the run cost, how long it took, the tokens it spent or the votes behind a rating. Each figure as its board printed it, one board per row.
| Board | Result | What the run cost | Also published |
|---|---|---|---|
| LiveBench coding | 94.3% | $0.9592 per task | Output tokens per task 15,315 |
| LiveBench reasoning | 87.2% | $0.0877 per task | Output tokens per task 14,539 |
| LiveBench data analysis | 73.0% | $0.1139 per task | Output tokens per task 18,701 |
| LiveBench research | 85.9% | $0.8179 per task | Output tokens per task 15,217 |
| LiveBench browser | 44.0% | $2.9177 per task | Output tokens per task 12,613 |
| LiveBench long agentic | 27.9% | $4.4983 per task | Output tokens per task 80,606 |
| LiveBench design | 78.1% | $0.3877 per task | Output tokens per task 24,466 |
| SWE-bench Verified (Vals AI) | 86.6% | $0.54 per test | Duration, as printed 3m 20s |
| Terminal-Bench 4 (Vals AI) | 8.6% | $5.52 per test | Duration, as printed 33m 43s |
| Vibe Code Bench (Vals AI) | 69.0% | $4.10 per test | Duration, as printed 13m 50s |
| Code migration (Vals AI) | 36.6% | $3.37 per test | Duration, as printed 23m 29s |
| ProgramBench (Vals AI) | 0.0% | $4.12 per test | Duration, as printed 18m 59s |
| SREBench (Vals AI) | 0.8% | $13.42 per test | Duration, as printed 1h 06m |
|---|---|---|---|
| IOI (Vals AI) | 40.6% | $5.64 per test | Duration, as printed 1h 27m |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | $0.28 per test | Duration, as printed 10m 24s |
| SkillsBench (Vals AI) | 66.0% | $0.58 per test | Duration, as printed 2m 16s |
| CyberBench (Vals AI) | 71.0% | $2.95 per test | Duration, as printed 14m 08s |
| Finance Agent (Vals AI) | 48.4% | $1.16 per test | Duration, as printed 4m 49s |
| Tax Agent Bench (Vals AI) | 24.9% | $0.47 per test | Duration, as printed 4m 44s |
| Legal Research Bench (Vals AI) | 38.0% | $1.09 per test | Duration, as printed 15m 54s |
| Excel Modeling Benchmark (Vals AI) | 52.9% | $1.55 per test | Duration, as printed 18m 28s |
| Vals Multimodal Index | 63.4% | $0.91 per test | Duration, as printed 5m 19s |
| DeepSWE | 53.8% | $2.4157 mean cost per task | Solved in 4 tries 77.9% · Output tokens per task 35,525 · Agent steps per task 61 |
| WeirdML | 46.4% | $0.0805 per run | Median lines of code 86 |
| ARC-AGI | 87.2% | $0.31 per task | Nothing else |
| ARC-AGI-2 | 52.6% | $0.78 per task | Nothing else |
| ProofBench | 31.0% | $0.574 per test | Time per proof 11m 09s |
| Surface Evolver Bench | 74.4% | $4.6103 of the run | Pass rate 50.0% · Tokens for the run 3.1M |
| ALE-Bench | 1309.3 | $0.1768 per problem | Tokens per problem 32,347 |
| LMArena WebDev | 1553 Elo | Not published | Votes 11,082 · Interval (±) ±6.7 |
| GPQA Diamond | 92.9% | Not published | Latency, as printed 3m 38s |
| MMLU Pro | 89.2% | Not published | Latency, as printed 5m 58s |
| LiveCodeBench (Vals AI) | 87.3% | Not published | Latency, as printed 9m 49s |
| MMMU Pro (Vals AI) | 61.8% | Not published | Latency, as printed 11m 55s |
| SAGE (Vals AI) | 35.0% | Not published | Latency, as printed 2m 50s |
| LegalBench (Vals AI) | 86.0% | Not published | Latency, as printed 1m 08s |
| CorpFin (Vals AI) | 67.4% | Not published | Latency, as printed 1m 32s |
| TaxEval (Vals AI) | 71.7% | Not published | Latency, as printed 3m 15s |
| MortgageTax (Vals AI) | 61.8% | Not published | Latency, as printed 1m 57s |
| MedCode (Vals AI) | 43.3% | Not published | Latency, as printed 60 s |
| MedScribe (Vals AI) | 86.9% | Not published | Latency, as printed 11m 45s |
| APEX-Agents | 56.2% | Not published | Mean score 70.5% |
| LMArena Text | 1448 Elo | Not published | Votes 39,896 · Interval (±) ±4.3 |
| LMArena Text: coding | 1474 Elo | Not published | Votes 11,116 · Interval (±) ±6.6 |
| LMArena Text: hard prompts | 1462 Elo | Not published | Votes 26,662 · Interval (±) ±5.0 |
| LMArena Text: math | 1459 Elo | Not published | Votes 1,766 · Interval (±) ±14.2 |
| LMArena Text: instruction following | 1446 Elo | Not published | Votes 14,539 · Interval (±) ±6.1 |
| LMArena Text: creative writing | 1442 Elo | Not published | Votes 8,298 · Interval (±) ±7.6 |
| LMArena Vision | 1287 Elo | Not published | Votes 12,599 · Interval (±) ±7.0 |
| LMArena Text: English | 1453 Elo | Not published | Votes 16,197 · Interval (±) ±5.7 |
| LMArena Text: non-English | 1440 Elo | Not published | Votes 23,697 · Interval (±) ±5.1 |
| LMArena Text: Chinese | 1495 Elo | Not published | Votes 3,066 · Interval (±) ±11.3 |
| LMArena Text: German | 1448 Elo | Not published | Votes 686 · Interval (±) ±23.0 |
| LMArena Text: Japanese | 1431 Elo | Not published | Votes 530 · Interval (±) ±27.5 |
| LMArena Text: Korean | 1406 Elo | Not published | Votes 731 · Interval (±) ±22.4 |
| LMArena Text: French | 1457 Elo | Not published | Votes 1,274 · Interval (±) ±18.1 |
| LMArena Text: Spanish | 1451 Elo | Not published | Votes 1,081 · Interval (±) ±18.5 |
| LMArena Text: Russian | 1449 Elo | Not published | Votes 4,639 · Interval (±) ±9.2 |
| LMArena Text: Polish | 1433 Elo | Not published | Votes 628 · Interval (±) ±23.5 |
| LMArena Text: multi-turn | 1456 Elo | Not published | Votes 6,632 · Interval (±) ±8.0 |
| LMArena Text: longer queries | 1463 Elo | Not published | Votes 19,283 · Interval (±) ±5.7 |
| LMArena Text: expert | 1466 Elo | Not published | Votes 4,720 · Interval (±) ±9.2 |
| LMArena Text: hard prompts in English | 1464 Elo | Not published | Votes 10,737 · Interval (±) ±6.7 |
| LMArena Text: software and IT | 1471 Elo | Not published | Votes 15,966 · Interval (±) ±5.8 |
| LMArena Text: mathematical work | 1481 Elo | Not published | Votes 2,161 · Interval (±) ±13.2 |
| LMArena Text: science | 1465 Elo | Not published | Votes 6,541 · Interval (±) ±7.8 |
| LMArena Text: medicine and healthcare | 1441 Elo | Not published | Votes 2,938 · Interval (±) ±11.6 |
| LMArena Text: legal and government | 1463 Elo | Not published | Votes 3,349 · Interval (±) ±10.9 |
| LMArena Text: business and finance | 1441 Elo | Not published | Votes 7,620 · Interval (±) ±7.5 |
| LMArena Text: writing and language | 1445 Elo | Not published | Votes 10,904 · Interval (±) ±6.7 |
| LMArena Text: entertainment and media | 1434 Elo | Not published | Votes 10,395 · Interval (±) ±6.9 |
| LMArena WebDev: React | 1556 Elo | Not published | Votes 7,531 · Interval (±) ±7.8 |
| LMArena WebDev: HTML | 1567 Elo | Not published | Votes 1,599 · Interval (±) ±16.2 |
| LMArena WebDev: from an image | 1562 Elo | Not published | Votes 4,255 · Interval (±) ±9.8 |
| LMArena Vision: English | 1285 Elo | Not published | Votes 4,285 · Interval (±) ±10.5 |
| LMArena Vision: Chinese | 1345 Elo | Not published | Votes 728 · Interval (±) ±23.3 |
| LMArena Vision: reading text | 1293 Elo | Not published | Votes 8,562 · Interval (±) ±7.5 |
| LMArena Vision: diagrams | 1304 Elo | Not published | Votes 3,227 · Interval (±) ±11.0 |
| LMArena Vision: homework | 1295 Elo | Not published | Votes 1,284 · Interval (±) ±17.1 |
| LMArena Vision: humor | 1276 Elo | Not published | Votes 573 · Interval (±) ±25.1 |
| LMArena Vision: creative writing | 1293 Elo | Not published | Votes 1,094 · Interval (±) ±19.0 |
| LMArena Search | 1216 Elo | Not published | Votes 76,458 · Interval (±) ±5.9 |
| LMArena Document | 1452 Elo | Not published | Votes 4,965 · Interval (±) ±8.7 |