Claude Haiku 4.5 vs Grok 4.20
Claude Haiku 4.5 leads Grok 4.20 on coding, 35.6 to 33.3 on the Vibe Coding Index, and Grok 4.20 costs 2.0x less per output token ($2.50 vs $5.00 per million). Updated October 22, 2026; 40 benchmarks have a result for both.
Claude Haiku 4.5 or Grok 4.20: which to pick
Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 33.3 for Grok 4.20.
Pick Grok 4.20 for output tokens 2.0x cheaper ($2.50 vs $5.00 per million) and a larger context window (2M against 200K tokens).
- Shared results
- 40
- Claude Haiku 4.5 only
- 55
- Grok 4.20 only
- 15
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Claude Haiku 4.5
Claude Haiku 4.5 scores 35.6 against 33.3.
4 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Grok 4.20
Grok 4.20 leads, 25.7 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Haiku 4.5 has a AA Agentic Index result, 8.0.
Directional only
Reasoning
GPQA Diamond
Grok 4.20
Grok 4.20 leads, 88.6% against 72.2%.
Same board, both measured
Math
AIME
Grok 4.20
Grok 4.20 leads, 96.5% against 82.7%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.20
Grok 4.20 leads, 86.3% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
Grok 4.20
Grok 4.20 leads, 1229 against 1122.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.20
Claude Haiku 4.5 $0.0035, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Claude Haiku 4.5
Claude Haiku 4.5 $0.56, Grok 4.20 $0.72.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Haiku 4.5 35.6 from 4 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
- Widest category
- Reasoning, 39.2 points apart on average over 4 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Claude Haiku 4.5 4.0% against Grok 4.20 65.1%, 61.1 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against Grok 4.20 $2.50 per million output tokens, 2.0x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, Grok 4.20 2M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Haiku 4.5 | Bars | Grok 4.20 | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 3 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 1 | ||
| Knowledge | 4 | 4 | ||
| Web design | 0 | 8 | ||
| General | 2 | 3 | ||
| All shared boards | 10 | 30 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index25
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | Not measured | Only Claude Haiku 4.5 measured |
| AA Coding Index | 43.9 | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Vals AI) | 41.2% | 84.3% | Grok 4.20 |
| SWE-bench Verified (Vals AI) | 66.6% | 72.2% | Grok 4.20 |
| Vibe Code Bench (Vals AI) | 11.4% | 4.1% | Claude Haiku 4.5 |
| Code migration (Vals AI) | 7.5% | 0.3% | Claude Haiku 4.5 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | 44.2% | Grok 4.20 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 37.9% | Only Grok 4.20 measured |
| Terminal-Bench | 35.5% | 57.3% | Grok 4.20 |
| WeirdML | 45.4% | 52.3% | Grok 4.20 |
| LMArena Text: coding | 1454 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: software and IT | 1439 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev: React | 1326 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev: HTML | 1318 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 25.7 | Grok 4.20 |
| Epoch Capabilities Index | 142.2 | 152.1 | Grok 4.20 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: agents building web apps | Not measured | 1144 | Only Grok 4.20 measured |
| Design Arena: agents building full-stack apps | Not measured | 1054 | Only Grok 4.20 measured |
| Design Arena: agents building mobile apps | Not measured | 1090 | Only Grok 4.20 measured |
| Design Arena: agents building Android apps | Not measured | 1045 | Only Grok 4.20 measured |
| Design Arena: agents building Godot games | Not measured | 1089 | Only Grok 4.20 measured |
| Design Arena: HTML slides | Not measured | 1180 | Only Grok 4.20 measured |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | 28.5% | Claude Haiku 4.5 |
| Tax Agent Bench (Vals AI) | 5.9% | 7.0% | Grok 4.20 |
| Legal Research Bench (Vals AI) | 10.6% | 13.9% | Grok 4.20 |
| Excel Modeling Benchmark (Vals AI) | 22.7% | 11.7% | Claude Haiku 4.5 |
| τ²-Bench Telecom | Not measured | 93.0% | Only Grok 4.20 measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | $4,663 | Grok 4.20 |
| Berkeley Function Calling Leaderboard (BFCL) | 68.7% | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 88.6% | Grok 4.20 |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | 83.5% | Grok 4.20 |
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.1% | Only Grok 4.20 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 34.5% | Only Grok 4.20 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI | 47.7% | 89.5% | Grok 4.20 |
| ARC-AGI-2 | 4.0% | 65.1% | Grok 4.20 |
| Chess puzzles | 8.0% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts | 1421 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: expert | 1443 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts in English | 1435 | Not measured | Only Claude Haiku 4.5 measured |
| Kagi LLM Benchmark | Not measured | 75.0% | Only Grok 4.20 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| AIME | 82.7% | 96.5% | Grok 4.20 |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 66.7% | Not measured | Only Claude Haiku 4.5 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: mathematical work | 1430 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index44
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | 86.3% | Grok 4.20 |
| LegalBench (Vals AI) | 81.2% | 77.7% | Claude Haiku 4.5 |
| CaseLaw (Vals AI) | 56.5% | 54.4% | Claude Haiku 4.5 |
| CorpFin (Vals AI) | 60.6% | 63.7% | Grok 4.20 |
| TaxEval (Vals AI) | 67.5% | 74.1% | Grok 4.20 |
| MortgageTax (Vals AI) | 62.2% | 45.4% | Claude Haiku 4.5 |
| MedQA (Vals AI) | 79.6% | 94.5% | Grok 4.20 |
| MedCode (Vals AI) | 32.7% | 32.2% | Claude Haiku 4.5 |
| SimpleQA Verified | 13.2% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: science | 1406 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: medicine and healthcare | 1394 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: legal and government | 1400 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: business and finance | 1400 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 1229 | Grok 4.20 |
| Design Arena: UI components | 1097 | 1200 | Grok 4.20 |
| Design Arena: game dev | 1097 | 1193 | Grok 4.20 |
| Design Arena: data viz | 1124 | 1217 | Grok 4.20 |
| Design Arena: 3D | 1071 | 1193 | Grok 4.20 |
| Design Arena: all code categories | 1114 | 1221 | Grok 4.20 |
| Design Arena: SVG | 1025 | 1165 | Grok 4.20 |
| Design Arena: ASCII art | 1140 | 1175 | Grok 4.20 |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | Not measured | Only Claude Haiku 4.5 measured |
| SAGE (Vals AI) | 31.8% | 38.2% | Grok 4.20 |
| MedScribe (Vals AI) | 85.2% | 63.4% | Claude Haiku 4.5 |
| Vals Multimodal Index | 42.9% | 39.1% | Claude Haiku 4.5 |
| IFBench | Not measured | 81.2% | Only Grok 4.20 measured |
| Long context reasoning (AA-LCR) | Not measured | 69.0% | Only Grok 4.20 measured |
| DTBench | 73.6% | 90.1% | Grok 4.20 |
| LMCA | 30.9% | 38.7% | Grok 4.20 |
| CL-bench | Not measured | 22.2% | Only Grok 4.20 measured |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| CL-bench Life | Not measured | 11.9% | Only Grok 4.20 measured |
| LMArena Text | 1397 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: instruction following | 1414 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: creative writing | 1371 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: English | 1414 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: non-English | 1377 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Chinese | 1418 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: German | 1374 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Japanese | 1338 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Korean | 1346 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: French | 1411 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Spanish | 1421 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Russian | 1381 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Polish | 1343 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: multi-turn | 1409 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: longer queries | 1427 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: writing and language | 1386 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: entertainment and media | 1369 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | Grok 4.20 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Grok 4.20 costs less
Repository review
50K input + 3K output tokens
Claude Haiku 4.5 costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 4.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Haiku 4.5 | SpaceXAI Grok 4.20 |
|---|---|---|
| Maker | Anthropic | xAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 15, 2025 | March 31, 2026 |
| Context window | 200K | 2M |
| Input $/Mtok | $1.00 | $1.25 |
| Output $/Mtok | $5.00 | $2.50 |
| Coding index | 35.6 | 33.3 |
| Independent measurements behind it | 4 | 2 |
| Cost per solved task | $0.56 | $0.72 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than Grok 4.20 for coding?
Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 33.3 for Grok 4.20. Pick Grok 4.20 for output tokens 2.0x cheaper ($2.50 vs $5.00 per million) and a larger context window (2M against 200K tokens).
Which is cheaper, Claude Haiku 4.5 or Grok 4.20?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Grok 4.20 $0.72.
Which has the bigger context window, Claude Haiku 4.5 or Grok 4.20?
Grok 4.20, with 2M tokens against 200K.
How many benchmarks is the Claude Haiku 4.5 vs Grok 4.20 comparison based on?
40 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.