As of October 20, 2026, SpaceXAI Grok 4.6 ranks #16 of 213 models overall with 44.3 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #7 of 203. SpaceXAI Grok 4.6 costs $2.00 per million input tokens and $6.00 per million output tokens. It was released on August 12, 2026.
Its output price ranks 260 of 349 priced models, counting from the cheapest.
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
x-ai/grok-4.6 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, GSO-Bench, MirrorCode, Cybench
Not measured on Design Arena: spreadsheets, SREBench (Vals AI), Harvey's Legal Agent Benchmark (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, LMArena Search
Not measured on MMMU Pro (Vals AI), Humanity's Last Exam, 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, Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver 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 | 89.1% | 20% |
| LMArena WebDevCoding | 1617 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 94.7% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 89.4% | Not in index |
| AA Intelligence IndexIntelligence | 44.3 | Not in index |
| AA Coding IndexCoding | 76.8 | Not in index |
| AA Agentic IndexAgentic work | 53.0 | Not in index |
| Design Arena: websitesWeb design | 1289 | Not in index |
| Design Arena: UI componentsWeb design | 1293 | Not in index |
| Design Arena: game devWeb design | 1296 | Not in index |
| Design Arena: data vizWeb design | 1283 | Not in index |
| Design Arena: 3DWeb design | 1277 | Not in index |
| Design Arena: all code categoriesWeb design | 1292 | Not in index |
| Design Arena: SVGWeb design | 1239 | Not in index |
| Design Arena: ASCII artWeb design | 1282 | Not in index |
| Design Arena: agents building web appsAgentic work | 1247 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1264 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1234 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1303 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1276 | Not in index |
| Design Arena: agents building gamesAgentic work | 1208 | Not in index |
| Design Arena: HTML slidesAgentic work | 1249 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1241 | 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 | 91.2% | Not in index |
| LiveBench data analysisGeneral | 75.3% | Not in index |
| LiveBench researchAgentic work | 84.5% | Not in index |
| LiveBench browserAgentic work | 64.0% | Not in index |
| LiveBench long agenticAgentic work | 40.7% | Not in index |
| LiveBench designWeb design | 79.8% | Not in index |
| LiveCodeBench (Vals AI)Coding | 88.2% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 95.6% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 17.2% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 76.2% | Not in index |
| Code migration (Vals AI)Coding | 44.6% | Not in index |
| ProgramBench (Vals AI)Coding | 1.0% | Not in index |
| SREBench (Vals AI)Agentic work | Not measured | Not in index |
| IOI (Vals AI)Coding | 47.6% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 78.3% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 14.8% | Not in index |
| SkillsBench (Vals AI)Coding | 55.8% | Not in index |
| CyberBench (Vals AI)Coding | 67.7% | Not in index |
| Finance Agent (Vals AI)Agentic work | 53.7% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 33.1% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 48.1% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 62.7% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 72.2% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 11.4% | Not in index |
| Vals Science IndexAgentic work | 38.1% | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 5.8% | 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 | 66.8% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 30.6% | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | 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 | 28.9% | Not in index |
| LegalBench (Vals AI)Knowledge | 86.3% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 66.2% | Not in index |
| TaxEval (Vals AI)Knowledge | 71.1% | Not in index |
| MortgageTax (Vals AI)Knowledge | 64.2% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 44.7% | Not in index |
| MedScribe (Vals AI)General | 86.5% | 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 | 94.9% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 44.1% | 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 | 56.5% | 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 | 81.0% | 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 | 67.5% | Not in index |
| FrontierCodeCoding | 48.0% | Not in index |
| FrontierSWECoding | 25.3% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 67.3% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 65.3% | 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 | 94.0% | Not in index |
| ARC-AGIReasoning | 87.5% | Not in index |
| ARC-AGI-2Reasoning | 67.1% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 75.9% | Not in index |
| Chess puzzlesReasoning | 33.0% | Not in index |
| Mystery game puzzlesReasoning | 34.0% | Not in index |
| EBR-benchReasoning | 30.5% | Not in index |
| OTIS Mock AIMEMath | 99.2% | Not in index |
| FrontierMath, tiers 1 to 3Math | 66.0% | Not in index |
| FrontierMath, tier 4Math | 31.7% | Not in index |
| ProofBenchMath | 51.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 49.3% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 97.3% | Not in index |
| LMCAGeneral | 48.5% | 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 | Not measured | Not in index |
| Furniture assemblyGeneral | 40.0% | 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 | 1508.1 | Not in index |
| Vending-Bench 2Agentic work | $9,047 | Not in index |
| Epoch Capabilities IndexIntelligence | 156.3 | Not in index |
| LMArena TextGeneral | 1428 | Not in index |
| LMArena Text: codingCoding | 1465 | Not in index |
| LMArena Text: hard promptsReasoning | 1447 | Not in index |
| LMArena Text: mathMath | 1416 | Not in index |
| LMArena Text: instruction followingGeneral | 1431 | Not in index |
| LMArena Text: creative writingGeneral | 1427 | Not in index |
| LMArena VisionGeneral | 1263 | Not in index |
| LMArena Text: EnglishGeneral | 1433 | Not in index |
| LMArena Text: non-EnglishGeneral | 1419 | Not in index |
| LMArena Text: ChineseGeneral | 1475 | Not in index |
| LMArena Text: GermanGeneral | 1432 | Not in index |
| LMArena Text: JapaneseGeneral | 1380 | Not in index |
| LMArena Text: KoreanGeneral | 1396 | Not in index |
| LMArena Text: FrenchGeneral | 1457 | Not in index |
| LMArena Text: SpanishGeneral | 1404 | Not in index |
| LMArena Text: RussianGeneral | 1422 | Not in index |
| LMArena Text: PolishGeneral | 1430 | Not in index |
| LMArena Text: multi-turnGeneral | 1424 | Not in index |
| LMArena Text: longer queriesGeneral | 1455 | Not in index |
| LMArena Text: expertReasoning | 1468 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1444 | Not in index |
| LMArena Text: software and ITCoding | 1457 | Not in index |
| LMArena Text: mathematical workMath | 1464 | Not in index |
| LMArena Text: scienceKnowledge | 1437 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1421 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1427 | Not in index |
| LMArena Text: business and financeKnowledge | 1416 | Not in index |
| LMArena Text: writing and languageGeneral | 1429 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1421 | Not in index |
| LMArena WebDev: ReactCoding | 1631 | Not in index |
| LMArena WebDev: HTMLCoding | 1597 | Not in index |
| LMArena WebDev: from an imageCoding | 1603 | Not in index |
| LMArena Vision: EnglishGeneral | 1270 | Not in index |
| LMArena Vision: ChineseGeneral | 1289 | Not in index |
| LMArena Vision: reading textGeneral | 1272 | Not in index |
| LMArena Vision: diagramsReasoning | 1285 | Not in index |
| LMArena Vision: homeworkReasoning | 1283 | Not in index |
| LMArena Vision: humorGeneral | 1270 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1262 | Not in index |
| LMArena SearchAgentic work | Not measured | 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 | 89.1% | $1.8584 per task | Output tokens per task 25,609 |
| LiveBench reasoning | 91.2% | $0.0873 per task | Output tokens per task 14,139 |
| LiveBench data analysis | 75.3% | $0.123 per task | Output tokens per task 19,229 |
| LiveBench research | 84.5% | $2.3255 per task | Output tokens per task 28,110 |
| LiveBench browser | 64.0% | $2.9212 per task | Output tokens per task 16,144 |
| LiveBench long agentic | 40.7% | $10.6258 per task | Output tokens per task 128,260 |
| LiveBench design | 79.8% | $1.2666 per task | Output tokens per task 46,787 |
| SWE-bench Verified (Vals AI) | 95.6% | $0.78 per test | Duration, as printed 10m 04s |
| Terminal-Bench 4 (Vals AI) | 17.2% | $5.06 per test | Duration, as printed 29m 25s |
| Vibe Code Bench (Vals AI) | 76.2% | $4.88 per test | Duration, as printed 25m 30s |
| Code migration (Vals AI) | 44.6% | $14.58 per test | Duration, as printed 1h 30m |
| ProgramBench (Vals AI) | 1.0% | $16.76 per test | Duration, as printed 4h 27m |
| IOI (Vals AI) | 47.6% | $8.18 per test | Duration, as printed 3h 57m |
|---|---|---|---|
| Terminal-Bench 2.1 (Vals AI) | 78.3% | $0.45 per test | Duration, as printed 10m 43s |
| Vibe Code Bench 1-100 (Vals AI) | 14.8% | $26.27 per test | Duration, as printed 2h 11m |
| SkillsBench (Vals AI) | 55.8% | $0.92 per test | Duration, as printed 13m 28s |
| CyberBench (Vals AI) | 67.7% | $4.07 per test | Duration, as printed 36m 52s |
| Finance Agent (Vals AI) | 53.7% | $1.66 per test | Duration, as printed 16m 41s |
| Tax Agent Bench (Vals AI) | 33.1% | $0.98 per test | Duration, as printed 10m 58s |
| Legal Research Bench (Vals AI) | 48.1% | $1.53 per test | Duration, as printed 25m 04s |
| Excel Modeling Benchmark (Vals AI) | 62.7% | $3.06 per test | Duration, as printed 52m 59s |
| BioMysteryBench (Vals AI) | 72.2% | $1.23 per test | Duration, as printed 14m 18s |
| Terminal-Bench-Science (Vals AI) | 11.4% | $4.82 per test | Duration, as printed 1h 18m |
| Vals Science Index | 38.1% | $2.45 per test | Duration, as printed 40m 10s |
| Public Benefits Bench (Vals AI) | 66.8% | $0.92 per test | Nothing else |
| MysteryMechanism (Vals AI) | 30.6% | $1.31 per test | Duration, as printed 27m 55s |
| DeepSWE | 67.5% | $3.449 mean cost per task | Solved in 4 tries 84.1% · Output tokens per task 49,764 · Agent steps per task 70 |
| FrontierSWE | 25.3% | $243.43 average cost per task | Best of 5 runs 37.3% · Hours per task 13.8 h |
| WeirdML | 67.3% | $0.3348 per run | Median lines of code 205 |
| ProofBench | 51.0% | $0.759 per test | Time per proof 14m 22s |
| ALE-Bench | 1508.1 | $0.2401 per problem | Tokens per problem 42,843 |
| LMArena WebDev | 1617 Elo | Not published | Votes 10,483 · Interval (±) ±7.3 |
| GPQA Diamond | 94.7% | Not published | Latency, as printed 3m 29s |
| MMLU Pro | 89.4% | Not published | Latency, as printed 55 s |
| LiveCodeBench (Vals AI) | 88.2% | Not published | Latency, as printed 1m 58s |
| SAGE (Vals AI) | 28.9% | Not published | Latency, as printed 3m 22s |
| LegalBench (Vals AI) | 86.3% | Not published | Latency, as printed 27 s |
| CorpFin (Vals AI) | 66.2% | Not published | Latency, as printed 24 s |
| TaxEval (Vals AI) | 71.1% | Not published | Latency, as printed 48 s |
| MortgageTax (Vals AI) | 64.2% | Not published | Latency, as printed 8.6 s |
| MedCode (Vals AI) | 44.7% | Not published | Latency, as printed 2m 07s |
| MedScribe (Vals AI) | 86.5% | Not published | Latency, as printed 1m 11s |
| APEX-Agents | 65.3% | Not published | Mean score 77.3% |
| LMArena Text | 1428 Elo | Not published | Votes 28,965 · Interval (±) ±4.8 |
| LMArena Text: coding | 1465 Elo | Not published | Votes 7,222 · Interval (±) ±7.7 |
| LMArena Text: hard prompts | 1447 Elo | Not published | Votes 18,782 · Interval (±) ±5.6 |
| LMArena Text: math | 1416 Elo | Not published | Votes 1,421 · Interval (±) ±15.8 |
| LMArena Text: instruction following | 1431 Elo | Not published | Votes 10,340 · Interval (±) ±6.8 |
| LMArena Text: creative writing | 1427 Elo | Not published | Votes 6,434 · Interval (±) ±8.5 |
| LMArena Vision | 1263 Elo | Not published | Votes 7,261 · Interval (±) ±8.3 |
| LMArena Text: English | 1433 Elo | Not published | Votes 11,735 · Interval (±) ±6.4 |
| LMArena Text: non-English | 1419 Elo | Not published | Votes 17,226 · Interval (±) ±5.7 |
| LMArena Text: Chinese | 1475 Elo | Not published | Votes 2,314 · Interval (±) ±12.8 |
| LMArena Text: German | 1432 Elo | Not published | Votes 507 · Interval (±) ±27.1 |
| LMArena Text: Japanese | 1380 Elo | Not published | Votes 497 · Interval (±) ±28.9 |
| LMArena Text: Korean | 1396 Elo | Not published | Votes 567 · Interval (±) ±25.8 |
| LMArena Text: French | 1457 Elo | Not published | Votes 840 · Interval (±) ±21.5 |
| LMArena Text: Spanish | 1404 Elo | Not published | Votes 789 · Interval (±) ±21.1 |
| LMArena Text: Russian | 1422 Elo | Not published | Votes 3,634 · Interval (±) ±10.2 |
| LMArena Text: Polish | 1430 Elo | Not published | Votes 436 · Interval (±) ±27.6 |
| LMArena Text: multi-turn | 1424 Elo | Not published | Votes 4,363 · Interval (±) ±9.5 |
| LMArena Text: longer queries | 1455 Elo | Not published | Votes 13,401 · Interval (±) ±6.4 |
| LMArena Text: expert | 1468 Elo | Not published | Votes 3,311 · Interval (±) ±10.7 |
| LMArena Text: hard prompts in English | 1444 Elo | Not published | Votes 7,574 · Interval (±) ±7.6 |
| LMArena Text: software and IT | 1457 Elo | Not published | Votes 10,857 · Interval (±) ±6.6 |
| LMArena Text: mathematical work | 1464 Elo | Not published | Votes 1,710 · Interval (±) ±14.7 |
| LMArena Text: science | 1437 Elo | Not published | Votes 4,815 · Interval (±) ±9.0 |
| LMArena Text: medicine and healthcare | 1421 Elo | Not published | Votes 2,044 · Interval (±) ±13.6 |
| LMArena Text: legal and government | 1427 Elo | Not published | Votes 2,481 · Interval (±) ±12.3 |
| LMArena Text: business and finance | 1416 Elo | Not published | Votes 5,368 · Interval (±) ±8.6 |
| LMArena Text: writing and language | 1429 Elo | Not published | Votes 8,265 · Interval (±) ±7.5 |
| LMArena Text: entertainment and media | 1421 Elo | Not published | Votes 7,591 · Interval (±) ±7.9 |
| LMArena WebDev: React | 1631 Elo | Not published | Votes 6,746 · Interval (±) ±8.7 |
| LMArena WebDev: HTML | 1597 Elo | Not published | Votes 1,670 · Interval (±) ±15.9 |
| LMArena WebDev: from an image | 1603 Elo | Not published | Votes 3,241 · Interval (±) ±11.1 |
| LMArena Vision: English | 1270 Elo | Not published | Votes 2,512 · Interval (±) ±12.9 |
| LMArena Vision: Chinese | 1289 Elo | Not published | Votes 380 · Interval (±) ±30.7 |
| LMArena Vision: reading text | 1272 Elo | Not published | Votes 4,881 · Interval (±) ±9.2 |
| LMArena Vision: diagrams | 1285 Elo | Not published | Votes 1,838 · Interval (±) ±14.2 |
| LMArena Vision: homework | 1283 Elo | Not published | Votes 873 · Interval (±) ±19.9 |
| LMArena Vision: humor | 1270 Elo | Not published | Votes 320 · Interval (±) ±32.5 |
| LMArena Vision: creative writing | 1262 Elo | Not published | Votes 714 · Interval (±) ±23.5 |
| LMArena Document | 1452 Elo | Not published | Votes 2,258 · Interval (±) ±12.0 |