As of October 21, 2026, Z.ai GLM 5.3 Flash ranks #21 of 213 models overall with 41.8 on the Artificial Analysis Intelligence Index. Its strongest category is agentic, where it ranks #8 of 87. Z.ai GLM 5.3 Flash costs $0.15 per million input tokens and $0.50 per million output tokens. It was released on August 26, 2026.
Its output price ranks 82 of 349 priced models, counting from the cheapest.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
z-ai/glm-5.3-flash 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), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, GSO-Bench, WeirdML, MirrorCode, Cybench
Not measured on Design Arena: agents building web apps, Design Arena: agents building full-stack apps, Design Arena: agents building mobile apps, Design Arena: agents building Android apps, Design Arena: agents building Godot games, Design Arena: agents building games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, BioMysteryBench (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search
Not measured on MysteryMechanism (Vals AI), Humanity's Last Exam, SimpleBench, 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), CorpFin (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MedCode (Vals AI), MMLU Pro (Artificial Analysis run), SimpleQA Verified, MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Public Benefits Bench (Vals AI), SAGE (Vals AI), Vals Multimodal Index, IFBench, DTBench, LMCA, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Document
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 | 80.6% | 20% |
| LMArena WebDevCoding | 1607 | 15% |
| Vals IndexGeneral | 50.9% | Not in index |
| GPQA DiamondReasoning | 86.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 86.1% | Not in index |
| AA Intelligence IndexIntelligence | 41.8 | Not in index |
| AA Coding IndexCoding | 71.5 | Not in index |
| AA Agentic IndexAgentic work | 50.9 | Not in index |
| Design Arena: websitesWeb design | 1272 | Not in index |
| Design Arena: UI componentsWeb design | 1316 | Not in index |
| Design Arena: game devWeb design | 1279 | Not in index |
| Design Arena: data vizWeb design | 1262 | Not in index |
| Design Arena: 3DWeb design | 1316 | Not in index |
| Design Arena: all code categoriesWeb design | 1282 | Not in index |
| Design Arena: SVGWeb design | 1284 | Not in index |
| Design Arena: ASCII artWeb design | 1269 | Not in index |
| Design Arena: agents building web appsAgentic work | Not measured | Not in index |
| Design Arena: agents building full-stack appsAgentic work | Not measured | Not in index |
| Design Arena: agents building mobile appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Android appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | Not measured | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | Not measured | 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 | 77.6% | Not in index |
| LiveBench data analysisGeneral | 76.4% | Not in index |
| LiveBench researchAgentic work | 70.1% | Not in index |
| LiveBench browserAgentic work | 84.0% | Not in index |
| LiveBench long agenticAgentic work | 28.4% | Not in index |
| LiveBench designWeb design | 77.2% | Not in index |
| LiveCodeBench (Vals AI)Coding | 80.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 92.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 37.4% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 30.8% | Not in index |
| Code migration (Vals AI)Coding | 20.5% | 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 | 52.5% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 62.9% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 16.0% | Not in index |
| SkillsBench (Vals AI)Coding | 40.2% | Not in index |
| CyberBench (Vals AI)Coding | 67.9% | Not in index |
| Finance Agent (Vals AI)Agentic work | 57.9% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 31.6% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 45.2% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 10.4% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 55.9% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 2.9% | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | Not measured | 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 | 86.0% | 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 | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | 83.9% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | Not measured | Not in index |
| TaxEval (Vals AI)Knowledge | 75.6% | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | Not measured | Not in index |
| MedScribe (Vals AI)General | 88.9% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 91.2% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 39.9% | 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 | 51.6% | 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 | 80.0% | 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 | Not measured | Not in index |
| FrontierCodeCoding | 31.8% | Not in index |
| FrontierSWECoding | 18.1% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | Not measured | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 52.8% | 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 | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 90.2% | Not in index |
| ARC-AGIReasoning | 91.0% | Not in index |
| ARC-AGI-2Reasoning | 65.8% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 21.0% | Not in index |
| Mystery game puzzlesReasoning | 8.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 93.9% | Not in index |
| FrontierMath, tiers 1 to 3Math | 55.8% | Not in index |
| FrontierMath, tier 4Math | 17.1% | Not in index |
| ProofBenchMath | 21.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | Not measured | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | Not measured | Not in index |
| LMCAGeneral | Not measured | 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 | 52.5% | Not in index |
| Furniture assemblyGeneral | Not measured | 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 | 303.6 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 153.1 | Not in index |
| LMArena TextGeneral | 1471 | Not in index |
| LMArena Text: codingCoding | 1507 | Not in index |
| LMArena Text: hard promptsReasoning | 1490 | Not in index |
| LMArena Text: mathMath | 1503 | Not in index |
| LMArena Text: instruction followingGeneral | 1478 | Not in index |
| LMArena Text: creative writingGeneral | 1441 | Not in index |
| LMArena VisionGeneral | 1294 | Not in index |
| LMArena Text: EnglishGeneral | 1474 | Not in index |
| LMArena Text: non-EnglishGeneral | 1462 | Not in index |
| LMArena Text: ChineseGeneral | 1531 | Not in index |
| LMArena Text: GermanGeneral | 1462 | Not in index |
| LMArena Text: JapaneseGeneral | 1444 | Not in index |
| LMArena Text: KoreanGeneral | 1436 | Not in index |
| LMArena Text: FrenchGeneral | 1491 | Not in index |
| LMArena Text: SpanishGeneral | 1475 | Not in index |
| LMArena Text: RussianGeneral | 1465 | Not in index |
| LMArena Text: PolishGeneral | 1450 | Not in index |
| LMArena Text: multi-turnGeneral | 1469 | Not in index |
| LMArena Text: longer queriesGeneral | 1481 | Not in index |
| LMArena Text: expertReasoning | 1511 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1488 | Not in index |
| LMArena Text: software and ITCoding | 1500 | Not in index |
| LMArena Text: mathematical workMath | 1497 | Not in index |
| LMArena Text: scienceKnowledge | 1484 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1475 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1473 | Not in index |
| LMArena Text: business and financeKnowledge | 1460 | Not in index |
| LMArena Text: writing and languageGeneral | 1455 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1440 | Not in index |
| LMArena WebDev: ReactCoding | 1624 | Not in index |
| LMArena WebDev: HTMLCoding | 1577 | Not in index |
| LMArena WebDev: from an imageCoding | 1578 | Not in index |
| LMArena Vision: EnglishGeneral | 1295 | Not in index |
| LMArena Vision: ChineseGeneral | 1363 | Not in index |
| LMArena Vision: reading textGeneral | 1299 | Not in index |
| LMArena Vision: diagramsReasoning | 1317 | Not in index |
| LMArena Vision: homeworkReasoning | 1318 | Not in index |
| LMArena Vision: humorGeneral | 1279 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1270 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | Not measured | 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 | 80.6% | $0.1696 per task | Output tokens per task 29,839 |
| Vals Index | 50.9% | $1.13 per test | Duration, as printed 1h 04m |
| LiveBench reasoning | 77.6% | $0.0138 per task | Output tokens per task 27,228 |
| LiveBench data analysis | 76.4% | $0.0243 per task | Output tokens per task 47,359 |
| LiveBench research | 70.1% | $0.187 per task | Output tokens per task 59,511 |
| LiveBench browser | 84.0% | $0.1769 per task | Output tokens per task 17,113 |
| LiveBench long agentic | 28.4% | $1.6288 per task | Output tokens per task 269,870 |
| LiveBench design | 77.2% | $0.0634 per task | Output tokens per task 38,912 |
| SWE-bench Verified (Vals AI) | 92.0% | $0.02 per test | Duration, as printed 1h 04m |
| Terminal-Bench 4 (Vals AI) | 37.4% | $1.22 per test | Duration, as printed 1h 01m |
| Vibe Code Bench (Vals AI) | 30.8% | $2.35 per test | Duration, as printed 1h 24m |
| Code migration (Vals AI) | 20.5% | $3.13 per test | Duration, as printed 3h 26m |
| ProgramBench (Vals AI) | 0.0% | $0.80 per test | Duration, as printed 5h 30m |
|---|---|---|---|
| SREBench (Vals AI) | 0.8% | $2.29 per test | Duration, as printed 3h 15m |
| IOI (Vals AI) | 52.5% | $0.43 per test | Duration, as printed 1h 32m |
| Terminal-Bench 2.1 (Vals AI) | 62.9% | $0.03 per test | Duration, as printed 16m 06s |
| Vibe Code Bench 1-100 (Vals AI) | 16.0% | $0.46 per test | Duration, as printed 39m 03s |
| SkillsBench (Vals AI) | 40.2% | $0.04 per test | Duration, as printed 12m 09s |
| CyberBench (Vals AI) | 67.9% | $0.14 per test | Duration, as printed 35m 48s |
| Finance Agent (Vals AI) | 57.9% | $0.05 per test | Duration, as printed 14m 51s |
| Tax Agent Bench (Vals AI) | 31.6% | $0.14 per test | Duration, as printed 21m 37s |
| Legal Research Bench (Vals AI) | 45.2% | $0.12 per test | Duration, as printed 51m 07s |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.4% | $0.32 per test | Duration, as printed 12m 25s |
| Excel Modeling Benchmark (Vals AI) | 55.9% | $0.71 per test | Duration, as printed 1h 15m |
| Terminal-Bench-Science (Vals AI) | 2.9% | $0.52 per test | Duration, as printed 3h 28m |
| FrontierSWE | 18.1% | $11.03 average cost per task | Best of 5 runs 28.4% · Hours per task 16.4 h |
| ProofBench | 21.0% | $0.2242 per test | Time per proof 1h 11m |
| Surface Evolver Bench | 52.5% | $0.3085 of the run | Pass rate 18.8% · Tokens for the run 2.6M |
| ALE-Bench | 303.6 | $0.0109 per problem | Tokens per problem 23,975 |
| LMArena WebDev | 1607 Elo | Not published | Votes 18,264 · Interval (±) ±6.6 |
| GPQA Diamond | 86.4% | Not published | Latency, as printed 2m 11s |
| MMLU Pro | 86.1% | Not published | Latency, as printed 45 s |
| LiveCodeBench (Vals AI) | 80.5% | Not published | Latency, as printed 5m 02s |
| MMMU Pro (Vals AI) | 86.0% | Not published | Latency, as printed 28 s |
| LegalBench (Vals AI) | 83.9% | Not published | Latency, as printed 13 s |
| TaxEval (Vals AI) | 75.6% | Not published | Latency, as printed 53 s |
| MedScribe (Vals AI) | 88.9% | Not published | Latency, as printed 1m 27s |
| APEX-Agents | 52.8% | Not published | Mean score 66.8% |
| LMArena Text | 1471 Elo | Not published | Votes 36,095 · Interval (±) ±4.8 |
| LMArena Text: coding | 1507 Elo | Not published | Votes 9,192 · Interval (±) ±7.2 |
| LMArena Text: hard prompts | 1490 Elo | Not published | Votes 22,985 · Interval (±) ±5.5 |
| LMArena Text: math | 1503 Elo | Not published | Votes 1,820 · Interval (±) ±14.2 |
| LMArena Text: instruction following | 1478 Elo | Not published | Votes 12,492 · Interval (±) ±6.5 |
| LMArena Text: creative writing | 1441 Elo | Not published | Votes 7,729 · Interval (±) ±7.8 |
| LMArena Vision | 1294 Elo | Not published | Votes 16,254 · Interval (±) ±6.4 |
| LMArena Text: English | 1474 Elo | Not published | Votes 13,229 · Interval (±) ±6.2 |
| LMArena Text: non-English | 1462 Elo | Not published | Votes 22,856 · Interval (±) ±5.5 |
| LMArena Text: Chinese | 1531 Elo | Not published | Votes 2,838 · Interval (±) ±11.8 |
| LMArena Text: German | 1462 Elo | Not published | Votes 614 · Interval (±) ±24.4 |
| LMArena Text: Japanese | 1444 Elo | Not published | Votes 692 · Interval (±) ±24.6 |
| LMArena Text: Korean | 1436 Elo | Not published | Votes 635 · Interval (±) ±24.2 |
| LMArena Text: French | 1491 Elo | Not published | Votes 1,348 · Interval (±) ±17.6 |
| LMArena Text: Spanish | 1475 Elo | Not published | Votes 1,360 · Interval (±) ±16.8 |
| LMArena Text: Russian | 1465 Elo | Not published | Votes 5,071 · Interval (±) ±9.0 |
| LMArena Text: Polish | 1450 Elo | Not published | Votes 610 · Interval (±) ±23.4 |
| LMArena Text: multi-turn | 1469 Elo | Not published | Votes 5,514 · Interval (±) ±8.7 |
| LMArena Text: longer queries | 1481 Elo | Not published | Votes 15,938 · Interval (±) ±6.3 |
| LMArena Text: expert | 1511 Elo | Not published | Votes 3,726 · Interval (±) ±10.3 |
| LMArena Text: hard prompts in English | 1488 Elo | Not published | Votes 8,456 · Interval (±) ±7.3 |
| LMArena Text: software and IT | 1500 Elo | Not published | Votes 13,518 · Interval (±) ±6.3 |
| LMArena Text: mathematical work | 1497 Elo | Not published | Votes 2,086 · Interval (±) ±13.3 |
| LMArena Text: science | 1484 Elo | Not published | Votes 5,949 · Interval (±) ±8.3 |
| LMArena Text: medicine and healthcare | 1475 Elo | Not published | Votes 2,450 · Interval (±) ±12.4 |
| LMArena Text: legal and government | 1473 Elo | Not published | Votes 2,957 · Interval (±) ±11.5 |
| LMArena Text: business and finance | 1460 Elo | Not published | Votes 6,577 · Interval (±) ±8.0 |
| LMArena Text: writing and language | 1455 Elo | Not published | Votes 9,977 · Interval (±) ±7.0 |
| LMArena Text: entertainment and media | 1440 Elo | Not published | Votes 9,197 · Interval (±) ±7.3 |
| LMArena WebDev: React | 1624 Elo | Not published | Votes 11,613 · Interval (±) ±7.4 |
| LMArena WebDev: HTML | 1577 Elo | Not published | Votes 2,703 · Interval (±) ±13.1 |
| LMArena WebDev: from an image | 1578 Elo | Not published | Votes 5,623 · Interval (±) ±9.1 |
| LMArena Vision: English | 1295 Elo | Not published | Votes 5,043 · Interval (±) ±9.8 |
| LMArena Vision: Chinese | 1363 Elo | Not published | Votes 699 · Interval (±) ±23.3 |
| LMArena Vision: reading text | 1299 Elo | Not published | Votes 11,021 · Interval (±) ±6.6 |
| LMArena Vision: diagrams | 1317 Elo | Not published | Votes 3,995 · Interval (±) ±10.1 |
| LMArena Vision: homework | 1318 Elo | Not published | Votes 2,229 · Interval (±) ±12.8 |
| LMArena Vision: humor | 1279 Elo | Not published | Votes 671 · Interval (±) ±23.5 |
| LMArena Vision: creative writing | 1270 Elo | Not published | Votes 1,355 · Interval (±) ±16.9 |