benchlm.ai
188 models · 151 benchmarks

Compare frontier AI models by quality, cost, and context

106 provisional-ranked models, 11 verified-ranked models, and 188 tracked LLMs. The most comprehensive LLM comparison tool — 151 benchmarks, real pricing, and runtime data in one place.

MethodologyProvidersAI Race

106 prov. / 11 ver.

Leaderboard

$0.30 avg output/M

LLM Pricing

Real-time TTFT & TPS

Speed Dashboard

24 agentic evals

Agent Benchmarks

−94% since 2023

Pricing Trends

CSV · JSON · Embed

Data Export

AgenticCodingMultimodalReasoningKnowledgeInst. FollowingMultilingualMath

Explore by Use Case

Additional reporting pages for long context, tool use, web research, computer use, document AI, image understanding, frontend work, and factuality.

Long Context

LongBench v2, MRCR, AI-Needle, Graphwalks

Tool Use

BFCL, MCP Atlas, Toolathlon, TAU Bench

Web Research

BrowseComp, WebArena, WebVoyager

Computer Use

OSWorld, ScreenSpot Pro, Vision2Web

Document AI

OfficeQA Pro, OmniDocBench, CC-OCR

Image Understanding

MMMU-Pro, AI2D, CountBench, RefCOCO

Frontend / App Dev

React Native Evals, Design2Code, Vision2Web

Factuality

SimpleQA, HLE w/o tools, Facts-VLM

The BenchLM LLM leaderboard 2026 provisionally ranks 106+ models and tracks 188+ large language models side by side across 151 benchmarks — from SWE-bench and LiveCodeBench for coding to GPQA Diamond and MMLU-Pro for knowledge and reasoning. Whether you need the best AI models 2026 has to offer for agentic workflows, math, multilingual tasks, or instruction following, our AI benchmark comparison tables make it easy to see how GPT-5, Claude, Gemini, DeepSeek, Llama, and dozens of other frontier and open-source models stack up on both benchmarks and operator tradeoffs like price and context. The main leaderboard now distinguishes provisional ranking from verified ranking so you can see which scores rest on exact-source coverage and which still rely on source-unverified public rows.

Compare models instantly

vs
Trending:Claude Opus 4.6 vs Gemini 3.1 ProClaude Opus 4.6 vs Grok 4.20Gemini 3.1 Pro vs Grok 4.20Claude Opus 4.6 vs GLM-5.1Gemini 3.1 Pro vs GLM-5.1

Decision-ready picks

The fastest way to scan the current BenchLM dataset by outcome instead of just by benchmark.

Best Overall

Gemini 3.1 Pro

85

overall score

Google

Best Open Weight

GLM-5 (Reasoning)

81

overall score

Z.AI

Cheapest

GLM-5 (Reasoning)

$0.00

avg / 1M tokens

Z.AI

Fastest

Mercury 2

789

tokens / sec

Inception

Lowest Latency

LFM2-24B-A2B

0.42s

TTFT

LiquidAI

Largest Context

Nemotron 3 Ultra 500B

10M

context window

NVIDIA

Pricing TrendsAgent BenchmarksData & Embed
The AI Race
Explore timeline
Current Crown(model released this month)

Claude Mythos Preview

Anthropic

81

Provider Podium

1st
Anthropic81.7
2nd
OpenAI81.7
3rd
Google81.3
6 months tracked89 total releases5 crown changes

Unified Model Leaderboard

Benchmarks, pricing, runtime signals, and context window in one table. Filter state syncs to the URL so every view is shareable. Provisional-ranked mode includes source-unverified non-generated benchmark evidence.

MethodologyProvidersAI Race
CSVJSON
188 models
Provisional-ranked mode includes source-unverified non-generated benchmark evidence.Score confidence:Full sourced coverageGood sourced coverageLimited sourced coverageEstimated
1
Gemini 3.1 Pro
Google
GoogleClosedCurrentStandard1M$1.25 / $5.0010929.71s8578778889819490591492.63
2
Claude Opus 4.6
Anthropic
AnthropicClosedCurrentStandard1M$15.00 / $75.00401.78s8482758285789590791496.61
3
GPT-5.3 Codex
OpenAI
OpenAIClosedCurrentReasoning400K$2.50 / $10.007988.26s~8481739391829388981416
4
Grok 4.1
xAI
xAIClosedSupersededStandard1M$3.00 / $15.00N/AN/A~8374699193819385931460.98
5
GPT-5.4
OpenAI
OpenAIClosedCurrentReasoning1.05M$2.50 / $15.0074151.79s8170748888839590811465.79
6
Claude Mythos Preview
Anthropic
AnthropicClosedCurrentReasoning1M$25.00 / $125.00N/AN/A817878—93759380——
7
Gemini 3 Pro Deep Think
Google
GoogleClosedCurrentReasoning2MN/AN/AN/A~8176668295768789961486.39
8
GLM-5 (Reasoning)
Z.AI
Z.AIOpenCurrentReasoning200K$0.00 / $0.00N/AN/A~8181668779748684941455.62
9
Claude Sonnet 4.6
Anthropic
AnthropicClosedCurrentStandard200K$3.00 / $15.00441.48s8076707892739086751462.21
10
GPT-5 (high)
OpenAI
OpenAIClosedEstablishedReasoning128KN/A8336.28s~8080718389738687721433.37
11
GLM-5.1
Z.AI
Z.AIOpenCurrentReasoning203K$1.40 / $4.40N/AN/A79787071—74—92901467.44
12
GPT-5.2
OpenAI
OpenAIClosedCurrentReasoning400K$2.00 / $8.0073130.34s~7968738287809285761439.54
13
Gemini 3 Pro
Google
GoogleClosedCurrentStandard2MN/A10932.65s~7871657586748685771486.16
14
GPT-5.2-Codex
OpenAI
OpenAIClosedCurrentReasoning400K$2.00 / $8.0012387.34s~7880699188758892961331
15
Claude Opus 4.5
Anthropic
AnthropicClosedCurrentStandard200KN/A461.01s7775686878738779951468
16
GPT-5.4 Pro
OpenAI
OpenAIClosedCurrentReasoning1.05M$30.00 / $180.0074151.79s777761839449—83551483.56
17
Qwen3.5 397B (Reasoning)
Alibaba
AlibabaOpenCurrentReasoning128K$0.00 / $0.00N/AN/A~7773678271728889931450
18
GPT-5.1
OpenAI
OpenAIClosedCurrentReasoning200K$1.50 / $6.0011157.47s~7775706992748886711438.53
19
GPT-5.1-Codex-Max
OpenAI
OpenAIClosedCurrentReasoning400K$2.00 / $8.00N/AN/A~7776709288748891961349
20
GLM-5
Z.AI
Z.AIOpenSupersededStandard200K$0.00 / $0.00741.64s7672657169738385901455.57
21
Kimi K2.5 (Reasoning)
Moonshot AI
Moonshot AIClosedCurrentReasoning128KN/AN/AN/A~7667737478689094711447
22
Gemma 4 31B
Google
GoogleOpenCurrentReasoning256K$0.00 / $0.00N/AN/A~73—78667761———1451.16
23
GLM-4.7
Z.AI
Z.AIOpenEstablishedReasoning200K$0.00 / $0.00821.10s~7362687971638485861442.71
24
GPT-5 (medium)
OpenAI
OpenAIClosedEstablishedReasoning128KN/A8336.28s~7370698288718888931328
25
Grok 4.1 Fast
xAI
xAIClosedCurrentStandard1MN/A1380.54s~7265558887718585941420
Showing 25 of 188

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.

Rankings

Best for CodingBest MultimodalBest for MathBest for ReasoningBest Agentic ModelsBest OverallBest Open SourceBest Chinese ModelsBest European ModelsLarge Context WindowReasoning ModelsProvider Rankings

Popular Comparisons

Claude Mythos Preview vs GPT-5.4 ProClaude Mythos Preview vs Claude Sonnet 4.6Claude 3.5 Sonnet vs Grok 4GPT-4o vs Grok 4.1Gemini 2.5 Pro vs o3Claude Sonnet 4.6 vs Grok 4.20GPT-4o vs Grok 4Claude 4.1 Opus (Thinking) vs Grok 4Claude Opus 4.6 vs Grok 4.1 Fast

Tools & Resources

LLM Pricing ComparisonCompare API costs across modelsAlternative FinderFind the best ChatGPT or Claude replacementWhich LLM Should I Use?Get a personalized recommendationCost CalculatorEstimate your monthly API spendMethodology & ExplainersHow BenchLM scores and curates benchmarks

Scoring Methodology

Each model's overall score is a normalized weighted average of category averages. Within each category, benchmark scores are combined using per-benchmark weights that favor harder, less-saturated evaluations. Scores are normalized so models with partial benchmark coverage are not unfairly penalized. Each score includes a confidence indicator (1-4 dots) showing how much sourced benchmark data supports it — models with no non-generated benchmark coverage are marked as estimated. Display-only benchmarks like MMLU, HumanEval, SWE-bench Verified, BBH, LisanBench, FLTEval, and the AIME/HMMT exams remain visible but are excluded from scoring.

Agentic22%
Coding20%
Reasoning17%
Multimodal & Grounded12%
Knowledge12%
Multilingual7%
Instruction Following5%
Math5%

Agentic

Weighted: Terminal-Bench 2.0 · BrowseComp · OSWorld-Verified

Coding

Weighted: SWE-bench Pro · LiveCodeBench · SWE-bench Verified. Display-only: HumanEval · FLTEval

Reasoning

Weighted: LongBench v2 · ARC-AGI-2 · MRCRv2 · MuSR. Display-only: BBH · LisanBench

Multimodal & Grounded

Weighted: MMMU-Pro · OfficeQA Pro

Knowledge

Weighted: GPQA · SuperGPQA · MMLU-Pro · HLE · FrontierScience · SimpleQA. Display-only: MMLU

Multilingual

Weighted: MGSM · MMLU-ProX

Instruction Following

Weighted: IFEval

Math

Weighted: AIME 2025 · BRUMO 2025 · MATH-500. Display-only: AIME 2023-2024 · HMMT 2023-2025

Data sourced from OpenBench, official model papers, and public leaderboards. Chatbot Arena Elo is tracked separately and not included in the overall score.