Claude Haiku 4.5 vs Gemini 2.5 Pro

Claude Haiku 4.5 leads Gemini 2.5 Pro on coding, 35.6 to 19.1 on the Vibe Coding Index, and Claude Haiku 4.5 costs 2.0x less per output token ($5.00 vs $10.00 per million). Updated October 22, 2026; 60 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Gemini 2.5 Pro

Claude Haiku 4.5Anthropic

Coding: 35.6
Overall: 41.0
Output $/M: $5.00

Gemini 2.5 ProGoogle

Coding: 19.1
Overall: 41.8
Output $/M: $10.00

vs boards won of 60 shared

Claude Haiku 4.5 or Gemini 2.5 Pro: which to pick

Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro.

Pick Gemini 2.5 Pro for a larger context window (1.05M against 200K tokens) and work measured by WeirdML or LMArena Text: software and IT, where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved task Model BGemini 2.5 ProGoogle19.1/1003 independent benchmarks$0.64 per solved task

603530

Shared results: 60
Claude Haiku 4.5 only: 35
Gemini 2.5 Pro only: 30
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 19.1.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Haiku 4.5
Claude Haiku 4.5 leads, 16.9 against 16.1.
Same board, both measured
Agentic work
AA Agentic Index
Claude Haiku 4.5
Claude Haiku 4.5 leads, 8.0 against 1.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Claude Haiku 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Haiku 4.5 has a MMLU Pro result, 78.7%.
Directional only
Web design
Design Arena: websites
Gemini 2.5 Pro
Gemini 2.5 Pro leads, 1167 against 1122.
Same board, both measured
Long documents
Listed context window
Gemini 2.5 Pro
Gemini 2.5 Pro takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 4.5
Claude Haiku 4.5 $0.0035, Gemini 2.5 Pro $0.0063 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Claude Haiku 4.5
Claude Haiku 4.5 $0.56, Gemini 2.5 Pro $0.64.
Published attempt cost and pass rate

At a glance

Coding index: Claude Haiku 4.5 35.6 from 4 benchmarks, Gemini 2.5 Pro 19.1 from 3 benchmarks.
Widest category: General, 10.9 points apart on average over 22 shared benchmarks.
Widest single gap: LMArena Text: Polish: Claude Haiku 4.5 1343 against Gemini 2.5 Pro 1479, 22.7 points apart on a 0 to 100 scale.
Output price: Claude Haiku 4.5 $5.00 against Gemini 2.5 Pro $10.00 per million output tokens, 2.0x apart.
Context window: Claude Haiku 4.5 takes 200K tokens, Gemini 2.5 Pro 1.05M.

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.

Boards won, where both have a result
Category	Claude Haiku 4.5	Gemini 2.5 Pro
Coding	8	2
Intelligence	1	1
Agentic work	2	1
Reasoning	1	5
Math	0	3
Knowledge	0	8
Web design	0	6
General	1	21
All shared boards	13	47

CodingLike-for-likeSix of these boards feed the Vibe Coding Index82

Coding benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
SWE-bench Verified	66.6%	53.6%	Claude Haiku 4.5
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	1226	Claude Haiku 4.5
AA Coding Index	43.9	33.3	Claude Haiku 4.5
LiveCodeBench (Vals AI)	41.2%	Not measured	Only Claude Haiku 4.5 measured
SWE-bench Verified (Vals AI)	66.6%	54.4%	Claude Haiku 4.5
Vibe Code Bench (Vals AI)	11.4%	0.4%	Claude Haiku 4.5
Code migration (Vals AI)	7.5%	Not measured	Only Claude Haiku 4.5 measured
ProgramBench (Vals AI)	0.0%	Not measured	Only Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)	43.8%	Not measured	Only Claude Haiku 4.5 measured
LiveCodeBench (Artificial Analysis run)	Not measured	80.1%	Only Gemini 2.5 Pro measured
SciCode	Not measured	46.3%	Only Gemini 2.5 Pro measured
Terminal-Bench Hard (Artificial Analysis run)	Not measured	26.5%	Only Gemini 2.5 Pro measured
Terminal-Bench	35.5%	32.6%	Claude Haiku 4.5
GSO-Bench	Not measured	3.9%	Only Gemini 2.5 Pro measured
WeirdML	45.4%	54.0%	Gemini 2.5 Pro
LMArena Text: coding	1454	1452	Claude Haiku 4.5
LMArena Text: software and IT	1439	1459	Gemini 2.5 Pro
LMArena WebDev: React	1326	Not measured	Only Claude Haiku 4.5 measured
LMArena WebDev: HTML	1318	1235	Claude Haiku 4.5
LMArena WebDev: from an image	Not measured	1285	Only Gemini 2.5 Pro measured
Neither model has a result on the other 17 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11

Intelligence benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
AA Intelligence Index	16.9	16.1	Claude Haiku 4.5
Epoch Capabilities Index	142.2	145.1	Gemini 2.5 Pro

Agentic workLike-for-likePublic boards, shown as published, kept out of the index21

Agentic work benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
AA Agentic Index	8.0	1.6	Claude Haiku 4.5
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%	Not measured	Only Claude Haiku 4.5 measured
Tax Agent Bench (Vals AI)	5.9%	Not measured	Only Claude Haiku 4.5 measured
Legal Research Bench (Vals AI)	10.6%	Not measured	Only Claude Haiku 4.5 measured
Excel Modeling Benchmark (Vals AI)	22.7%	Not measured	Only Claude Haiku 4.5 measured
τ²-Bench Telecom	Not measured	54.1%	Only Gemini 2.5 Pro measured
GDPval	Not measured	23.3%	Only Gemini 2.5 Pro measured
BALROG	31.2%	Not measured	Only Claude Haiku 4.5 measured
DeepResearch Bench	45.5%	41.5%	Claude Haiku 4.5
Vending-Bench 2	$459	$574	Gemini 2.5 Pro
Berkeley Function Calling Leaderboard (BFCL)	68.7%	Not measured	Only Claude Haiku 4.5 measured
BrowseComp-Plus	Not measured	29.5%	Only Gemini 2.5 Pro measured
Neither model has a result on the other 26 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index15

Reasoning benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
GPQA Diamond	72.2%	Not measured	Only Claude Haiku 4.5 measured
LiveBench reasoning	61.7%	Not measured	Only Claude Haiku 4.5 measured
MMMU Pro (Vals AI)	46.1%	Not measured	Only Claude Haiku 4.5 measured
GPQA Diamond (Artificial Analysis run)	Not measured	84.4%	Only Gemini 2.5 Pro measured
Humanity's Last Exam (Artificial Analysis run)	Not measured	22.5%	Only Gemini 2.5 Pro measured
GPQA Diamond (Epoch AI run)	71.2%	85.3%	Gemini 2.5 Pro
ARC-AGI	47.7%	41.0%	Claude Haiku 4.5
ARC-AGI-2	4.0%	4.9%	Gemini 2.5 Pro
Chess puzzles	8.0%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: hard prompts	1421	1455	Gemini 2.5 Pro
LMArena Text: expert	1443	1452	Gemini 2.5 Pro
LMArena Text: hard prompts in English	1435	1453	Gemini 2.5 Pro
LMArena Vision: diagrams	Not measured	1274	Only Gemini 2.5 Pro measured
LMArena Vision: homework	Not measured	1281	Only Gemini 2.5 Pro measured
Kagi LLM Benchmark	Not measured	70.3%	Only Gemini 2.5 Pro measured
Neither model has a result on the other 7 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index03

Math benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
AIME	82.7%	Not measured	Only Claude Haiku 4.5 measured
MGSM (Vals AI)	92.2%	Not measured	Only Claude Haiku 4.5 measured
AA Math Index	Not measured	87.7	Only Gemini 2.5 Pro measured
AIME 2025 (Artificial Analysis run)	Not measured	87.7%	Only Gemini 2.5 Pro measured
OTIS Mock AIME	66.7%	84.7%	Gemini 2.5 Pro
FrontierMath, tiers 1 to 3	Not measured	24.6%	Only Gemini 2.5 Pro measured
FrontierMath, tier 4	Not measured	0.0%	Only Gemini 2.5 Pro measured
MATH level 5	96.4%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: math	1398	1450	Gemini 2.5 Pro
LMArena Text: mathematical work	1430	1454	Gemini 2.5 Pro
Neither model has a result on the other 3 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08

Knowledge benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
MMLU Pro	78.7%	Not measured	Only Claude Haiku 4.5 measured
LegalBench (Vals AI)	81.2%	Not measured	Only Claude Haiku 4.5 measured
CaseLaw (Vals AI)	56.5%	63.9%	Gemini 2.5 Pro
CorpFin (Vals AI)	60.6%	60.8%	Gemini 2.5 Pro
TaxEval (Vals AI)	67.5%	Not measured	Only Claude Haiku 4.5 measured
MortgageTax (Vals AI)	62.2%	68.9%	Gemini 2.5 Pro
MedQA (Vals AI)	79.6%	Not measured	Only Claude Haiku 4.5 measured
MedCode (Vals AI)	32.7%	50.6%	Gemini 2.5 Pro
MMLU Pro (Artificial Analysis run)	Not measured	86.2%	Only Gemini 2.5 Pro measured
SimpleQA Verified	13.2%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: science	1406	1480	Gemini 2.5 Pro
LMArena Text: medicine and healthcare	1394	1476	Gemini 2.5 Pro
LMArena Text: legal and government	1400	1480	Gemini 2.5 Pro
LMArena Text: business and finance	1400	1439	Gemini 2.5 Pro
FACTS Benchmark Suite	Not measured	61.5%	Only Gemini 2.5 Pro measured
Neither model has a result on the other 3 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index06

Web design benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	Leader
Design Arena: websites	1122	1167	Gemini 2.5 Pro
Design Arena: UI components	1097	1137	Gemini 2.5 Pro
Design Arena: game dev	1097	1111	Gemini 2.5 Pro
Design Arena: data viz	1124	1222	Gemini 2.5 Pro
Design Arena: 3D	1071	1080	Gemini 2.5 Pro
Design Arena: all code categories	1114	1152	Gemini 2.5 Pro
Design Arena: SVG	1025	Not measured	Only Claude Haiku 4.5 measured
Design Arena: ASCII art	1140	Not measured	Only Claude Haiku 4.5 measured
LiveBench design	59.9%	Not measured	Only Claude Haiku 4.5 measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index121

General benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	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%	41.9%	Gemini 2.5 Pro
MedScribe (Vals AI)	85.2%	73.5%	Claude Haiku 4.5
Vals Multimodal Index	42.9%	Not measured	Only Claude Haiku 4.5 measured
IFBench	Not measured	48.7%	Only Gemini 2.5 Pro measured
Long context reasoning (AA-LCR)	Not measured	69.0%	Only Gemini 2.5 Pro measured
DTBench	73.6%	82.4%	Gemini 2.5 Pro
LMCA	30.9%	34.8%	Gemini 2.5 Pro
Creative writing (Lech Mazur)	Not measured	83.8%	Only Gemini 2.5 Pro measured
ExploitBench	13.7%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text	1397	1458	Gemini 2.5 Pro
LMArena Text: instruction following	1414	1437	Gemini 2.5 Pro
LMArena Text: creative writing	1371	1454	Gemini 2.5 Pro
LMArena Vision	Not measured	1263	Only Gemini 2.5 Pro measured
LMArena Text: English	1414	1458	Gemini 2.5 Pro
LMArena Text: non-English	1377	1452	Gemini 2.5 Pro
LMArena Text: Chinese	1418	1507	Gemini 2.5 Pro
LMArena Text: German	1374	1487	Gemini 2.5 Pro
LMArena Text: Japanese	1338	1461	Gemini 2.5 Pro
LMArena Text: Korean	1346	1434	Gemini 2.5 Pro
LMArena Text: French	1411	1473	Gemini 2.5 Pro
LMArena Text: Spanish	1421	1474	Gemini 2.5 Pro
LMArena Text: Russian	1381	1461	Gemini 2.5 Pro
LMArena Text: Polish	1343	1479	Gemini 2.5 Pro
LMArena Text: multi-turn	1409	1453	Gemini 2.5 Pro
LMArena Text: longer queries	1427	1449	Gemini 2.5 Pro
LMArena Text: writing and language	1386	1454	Gemini 2.5 Pro
LMArena Text: entertainment and media	1369	1441	Gemini 2.5 Pro
LMArena Vision: English	Not measured	1261	Only Gemini 2.5 Pro measured
LMArena Vision: Chinese	Not measured	1300	Only Gemini 2.5 Pro measured
LMArena Vision: reading text	Not measured	1270	Only Gemini 2.5 Pro measured
LMArena Vision: humor	Not measured	1262	Only Gemini 2.5 Pro measured
LMArena Vision: captioning	Not measured	1304	Only Gemini 2.5 Pro measured
LMArena Vision: recognizing things	Not measured	1283	Only Gemini 2.5 Pro measured
LMArena Vision: creative writing	Not measured	1265	Only Gemini 2.5 Pro measured
LMArena Document	1420	1421	Gemini 2.5 Pro
Neither model has a result on the other 9 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Claude Haiku 4.5 and Gemini 2.5 Pro
Benchmark	Claude Haiku 4.5	Gemini 2.5 Pro	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

Claude Haiku 4.5$0.0035Fits in one request

Gemini 2.5 Pro$0.0063Fits in one request

Claude Haiku 4.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request

Gemini 2.5 Pro$0.092Fits in one request

Claude Haiku 4.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window

Gemini 2.5 Pro$0.350Fits in one request

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.

Specifications of Claude Haiku 4.5 and Gemini 2.5 Pro
Specification	Anthropic Claude Haiku 4.5	Google Gemini 2.5 Pro
Maker	Anthropic	Google
Weights	No public weights listed	No public weights listed
Released	October 15, 2025	June 17, 2025
Context window	200K	1.05M
Input $/Mtok	$1.00	$1.25
Output $/Mtok	$5.00	$10.00
Coding index	35.6	19.1
Independent measurements behind it	4	3
Cost per solved task	$0.56	$0.64
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Haiku 4.5 better than Gemini 2.5 Pro for coding?

Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro. Pick Gemini 2.5 Pro for a larger context window (1.05M against 200K tokens) and work measured by WeirdML or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Haiku 4.5 or Gemini 2.5 Pro?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Gemini 2.5 Pro $0.64.

Which has the bigger context window, Claude Haiku 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Gemini 2.5 Pro comparison based on?

60 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 Gemini 2.5 Pro's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-haiku-4-5-vs-gemini-2-5-pro" title="Claude Haiku 4.5 vs Gemini 2.5 Pro, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-haiku-4-5-vs-gemini-2-5-pro">LLMBenchmark.ai, Claude Haiku 4.5 vs Gemini 2.5 Pro</a></p>

Claude Haiku 4.5 or Gemini 2.5 Pro: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next