LeadsCalc
Interactive leaderboard

Best AI Models for Math 2026: Quantitative LLM Workloads

Compare top math LLMs in 2026 with GSM8K and MATH benchmarks alongside live API pricing. For finance, STEM, and analytics teams in the US, Canada, and Australia.

Math-focused LLM rankings with API spend context in 2026

Math-heavy workloads punish silent errors. This tab emphasizes quantitative benchmarks while surfacing estimated API cost so data and engineering groups in the United States, Canada, and Australia can pair accuracy targets with budget reality—before they commit to a model for spreadsheets, tutoring copilots, or internal calculators.

Est. monthlyROI scoreCodingReasoningSpeedMathContextOverallOpen-weight

Workload & pricing toggles

Workload presets

Same three scenarios as the main AI API calculator: moderate traffic, large RAG-style context, or per-request max tokens with a lower request count.

Include Vision / Image Processing

Off — no image fees in cost estimates for vision-capable models.

Turn On to include image fees.

OffOn

Use Cached Pricing

Enable to get 50% off input tokens where cached rates apply

OffOn

Deep Reasoning / Thinking Mode

Model hidden reasoning / extended thinking charged like output tokens when enabled.

OffOn

Batch Pricing

Enable for 50% off input & output where batch/async pricing applies

OffOn
≈ $100.00/mo
8K
1K—1.0M
≈ $100.00/mo
2K
100—500K
≈ $200.00 total
5K
10—100K

Cached / batch est. monthly values only change after the pipeline sets supports_caching or supports_batch in Supabase. The toggles here narrow the table to models whose catalog or provider typically supports those modes.

Magic quadrant (top 15)

X: est. monthly · Y: Math · Dot: provider color · Hover for rank, model & details

Full leaderboard

Showing 48 of 513 models.

PickModelEst. monthlyROI scoreCodingReasoningSpeedMathContextOverall
OpenAI: o3 Pro$1,600.0059
98
92
40
99
200K
95SWE-bench Verified at 69.1% maps to 98 coding. GPQA Diamond at 83.3% maps to 98 logic. AIME 2024 at 91.6% maps to 99 math. As a flagship reasoning model, speed is lower (40).
OpenAI: GPT-6 Astra$900.0061
98
97
55
99
1.1M
98DeepSWE 74.1% maps to 98 coding. GPQA Diamond 96% maps to 99 logic. FrontierMath 97.6% maps to 99 math. MMMU 74.8% maps to 85 multimodal. Flagship reasoning model speed is estimated at 55.
OpenAI: GPT Sol Latest$180.0062
96
97
45
99
1.1M
97SWE-bench Pro at 64.6% maps to 96 coding. GPQA Diamond at 94.6% maps to 98 logic. FrontierMath at 89.0% maps to 99 math. Speed is 45 based on 27.2 tokens/s throughput for this flagship reasoning model.
OpenAI: GPT-6 Astra Pro$900.0062
98
99
45
99
1.1M
99DeepSWE 74.1% maps to 98 coding. GPQA Diamond 96% maps to 99 logic. FrontierMath 97.6% maps to 99 math. MMMU 74.8% maps to 85 multimodal. Flagship reasoning model with native effort controls, yielding lower speed (45).
xAI: Grok 3 Beta$270.0060
92
93
50
98
131K
94GPQA Diamond 84.6% and AIME 93.3% (Think mode) map to near-max logic/math. LiveCodeBench 79.4% maps to high coding. MMMU 78% confirms strong vision. Flagship tier; speed inferred moderate due to reasoning.
OpenAI: GPT-6.1 Sol$180.0058
75
92
75
98
1.1M
89Based on GPT-5.6 Sol evidence: SWE-bench 74.6% (Coding 75), GPQA 89.6% (Logic 90), MATH 97.8% (Math 98). Positioned below flagship Astra, mapped as a strong mid-tier model with native reasoning.
OpenAI: o3 Mini High$88.0059
85
87
65
98
200K
89GPQA 79.7% (Logic 88), MATH 97.9% (Math 98), HumanEval 97% (Coding 85). As a Mini tier model with high reasoning effort, it achieves flagship-level STEM scores but operates slower than standard minis due to extended chain-of-thought.
DeepSeek R1$53.0062
88
89
40
98
64K
91MMLU at 90.8% maps Logic to 92. MATH at 97.3% maps Math to 98. Coding inferred at 88 for o1-class flagship. Speed set to 40 due to 2-4x slower reasoning token generation. No vision supported.
Arcee AI: Trinity Large Thinking$18.0068
95
94
45
98
262K
95SWE-bench Verified at 63.2% maps to 95 coding. GPQA-Diamond at 76.3% maps to 95 logic. AIME 2025 at 96.3% maps to 98 math. As a heavy reasoning model (398B MoE), speed is mapped to 45.
Reflection: Beam 1.0 501B A23B$20.0067
95
93
45
98
1.0M
95SWE-bench Verified 80.9% maps to 95 coding. GPQA Diamond 90.5% maps to 96 logic. AIME 97.8% maps to 98 math. Heavyweight MoE reasoning model; speed mapped to 45.
MoonshotAI: Kimi K2.5$45.0064
95
93
65
98
262K
95SWE-bench Verified 76.8% maps to 95 coding. GPQA Diamond 87.9% maps to 96 logic. AIME 2025 96.1% maps to 98 math. 1T MoE flagship tier; native reasoning supported.
OpenAI: GPT-5.2$210.0062
96
96
50
98
400K
97SWE-bench Verified 68.1% maps to 96 coding. GPQA 81.4% maps to 97 logic. MMMU 81.6% maps to 95 multimodal. Frontier reasoning model; speed estimated at 50.
OpenAI: GPT-6.1 Sol Pro$180.0058
75
92
40
98
1.1M
89SWE-bench at 74.6 maps to 75 coding. GPQA at 89.6% maps to 90 logic. MATH at 97.8% maps to 98 math. As a 'Pro' reasoning model, speed is mapped lower (40).
OpenAI: o1-pro$12,000.0056
85
93
40
98
200K
92GPQA 78.0% maps to 95 logic. SWE-bench Verified 48.9% maps to 85 coding. GSM8K 97.1% maps to 98 math. MMMU 77.6% maps to 85 multimodal. Speed is 40 due to heavy reasoning architecture.
OpenAI: o4 Mini High$88.0059
85
85
65
98
200K
88Evidence cites AIME at 99.5% (Math: 98). SWE-bench outpaces o3-mini (Coding: 85). As a Mini-tier reasoning model, Logic (85) and Speed (65) reflect its high reasoning effort and fast architecture. Multimodal (80) supported by MMMU/MathVista claims.
OpenAI: o1$1,200.0058
88
93
40
98
200K
93SWE-bench Verified 48.9% maps to 88 coding. GPQA 78% maps to 96 logic. MMMU 77.6% maps to 85 multimodal. Speed is 40 due to extended reasoning times. Flagship tier.
OpenAI: o3 Deep Research$800.0059
98
92
35
98
200K
95SWE-bench Verified 69.1% maps to 98 coding. GPQA Diamond 83.3% maps to 98 logic. MMMU 82.9% maps to 95 multimodal. Speed is 35 due to extended reasoning times.
MoonshotAI: Kimi K3$117.5662
95
93
65
98
1.0M
95SWE-bench Verified at 76.8% maps to 95 coding. GPQA-Diamond at 87.6% maps to 95 logic. IFEval 89.8% maps to 90 instruction. AIME 96.1% maps to 98 math. 2.8T MoE tier dictates ~65 speed.
o3$160.0061
96
91
40
98
200K
94SWE-bench Verified at 69.1% maps to 96 coding. GPQA Diamond at 87.7% maps to 97 logic. AIME 2024 at 96.7% maps to 98 math. Speed is 40 due to extended reasoning times.
Z.ai: GLM 4.5$46.0063
90
90
60
98
131K
92SWE-bench Verified 64.2% maps to 90 coding. GPQA 79.1% maps to 92 logic. MATH-500 98.2% maps to 98 math. Flagship MoE model with native thinking mode; speed mapped to 60 based on 41.5 tokens/s.
OpenAI: o3 Mini$88.0063
95
93
65
98
200K
95SWE-bench Verified (69.1%) maps to 95 coding. GPQA (83.3%) maps to 92 logic. Despite being a 'Mini' tier model, its native reasoning capabilities yield flagship-level STEM scores, though speed is balanced for chain-of-thought generation.
DeepSeek: R1 0528$41.5065
92
94
45
98
164K
95GPQA 81.0% maps to 98 logic. AIME 2024 91.4% maps to 98 math. LiveCodeBench 73.3% maps to 92 coding. Speed reflects 287 c/s but heavy reasoning overhead (23K thinking tokens).
Qwen: Qwen3 Next 80B A3B Thinking$18.0067
90
93
45
97
262K
93GPQA at 77.2% maps to 96 logic. IFEval at 88.9% maps to 90 instruction. AIME 2025 at 87.8% maps to 97 math. As an 80B thinking model, speed is lower (45). No SWE-bench cited; coding estimated at 90.
Z.ai: GLM 5.1$100.0062
98
93
65
97
205K
95SWE-bench Pro top score (GLM-5 had 77.8, +3.3 gain) maps to 98 coding. GPQA Diamond 86.2% maps to 95 logic. AIME 95.3% maps to 97 math. Heavyweight MoE tier yields 65 speed.
OpenAI: GPT-5.6 Sol$360.0058
91
88
60
97
1.1M
91Lacking explicit GPT-5.6 Sol benchmarks, inferred flagship scores from top leaderboard entries (SWE-bench ~91%, GSM8K ~97%) and GPT-4.5 GPQA (71.4%). Mapped to 85-97 range for logic/coding/math. Speed set to 60 for heavyweight tier.
Qwen: Qwen3.6 Max Preview$102.7063
96
95
55
97
262K
96Based on Qwen3.6 Plus scoring SWE-bench 78.8% and GPQA 90.4%, Max (1T MoE flagship) maps to 96 for coding and logic. Native reasoning is supported via <think> tags. Vision defaults to frontier pricing.
Anthropic: Claude Sonnet Latest$180.0061
95
94
80
96
1.0M
95Claude 3.7 Sonnet scores SWE-bench Verified 72.7% (Coding: 95), GPQA Diamond 84.8% (Logic: 95), MATH 96.2% (Math: 96), IFEval 93.2% (Instruction: 93), MMMU 75% (Multimodal: 75). Mid-tier speed (~80). Features native extended thinking.
Google: Gemini 2.5 Pro Preview 06-05$150.0062
96
93
45
96
1.0M
95SWE-bench (59.6%) maps to 96 coding. GPQA (86.4%) maps to 96 logic. AIME (88.0%) maps to 96 math. MMMU (82.0%) maps to 90 multimodal. Flagship tier model with native reasoning; speed adjusted for thinking overhead.
DeepSeek: DeepSeek V3.2 Speciale$15.7969
95
97
45
96
164K
96GPQA 87.1% maps to 98 logic. LiveCodeBench 89.6% and Aider 88.0% map to 95 coding. HMMT 99.0% maps to 96 math. Flagship reasoning model with native thinking tokens; speed scored 45 due to extended reasoning overhead.
Anthropic: Claude Sonnet 5$180.0062
98
96
80
96
1.0M
96SWE-bench 72.7% maps to 98 coding. GPQA Diamond 84.8% maps to 98 logic. IFEval 93.2% maps to 93 instruction. MATH 96.2% maps to 96 math. MMMU 75% maps to 85 multimodal. Sonnet-class speed estimated at 80.
PrismML: Ternary Bonsai 2 27B$8.0069
89
87
45
96
262K
90HumanEval+ 95.12% and MMLU-Redux 89.09% map to coding (89) and logic (85). MATH-500 98.80% yields exceptional math (96). As a 27B reasoning model, speed is lower (45) due to default xhigh thinking effort.
Z.ai: GLM 5.3 Prime$200.0061
95
93
75
96
1.0M
94SWE-bench Verified 77.8% maps to 95 coding. GPQA 78.0% maps to 95 logic. MATH 96.4% maps to 96 math. Speed is 30 tokens/s (75). High-speed 'Prime' variant retains flagship reasoning capabilities.
OpenAI: GPT-5.1-Codex$150.0060
88
92
60
96
400K
92PricePerToken cites GPQA 86.0%, Math 95.7%, and Coding 36.6% (likely SWE-bench). Mapped GPQA to Logic 94, Coding to 88, and Math to 96. Speed reflects 27.4 tok/s throughput.
Perplexity: Sonar Reasoning Pro$160.0058
85
87
45
96
128K
89Evidence cites GPQA Diamond at 62.3% (Logic 88) and MATH-500 at 92.1% (Math 96). MMLU is 83.0%. As an R1-based reasoning model, speed is lower (45), while coding is inferred high (85) from its flagship tier.
Z.ai: GLM 4.7$41.4063
90
90
65
96
205K
92SWE-bench Verified 73.8 maps to 90 coding. GPQA Diamond 85.7 maps to 92 logic. IFEval 88.0 maps to 88 instruction. AIME 2025 95.7 maps to 96 math. Flagship tier speed estimated at 65.
Qwen: Qwen3 Max Thinking$70.2062
90
93
45
96
262K
93Evidence lacks exact Qwen3 Max Thinking scores but notes it's the flagship reasoning model. Inferred from Qwen2.5 72B (HumanEval 86.6%, GSM8K 95.8%) and VL 32B comparisons; mapped Coding to 90, Logic to 92. Speed reflects heavy reasoning tier.
Qwen: Qwen3.5-Flash$5.2074
88
92
95
95
1.0M
92SWE-bench Verified at 69.2% maps to 88 coding. GPQA Diamond at 84.2% maps to 92 logic. IFEval 91.9% maps to 92 instruction. As a Flash tier, speed is 95, though its reasoning capabilities rival flagship models.
Sakana: Sakana Namazu$78.0060
88
88
65
95
262K
90GPQA Diamond (81.3%) maps to Logic 90. AIME'25 (90.6%) maps to Math 95. Heavyweight tier (DeepSeek/Llama-405B base) infers Coding 88 and Speed 65. Vision inferred at 80 with default frontier price.
Google: Gemini 3.1 Pro Preview Custom Tools$200.0062
98
97
65
95
1.0M
97SWE-bench Verified at 80.6% maps to 98 coding. GPQA Diamond at 94.3% maps to 98 logic. As a flagship Pro model, it receives high multimodal (95) and math (95) scores, with standard heavyweight speed (65).
Google: Gemini 2.5 Pro Preview 05-06$150.0061
95
93
45
95
1.0M
94Evidence notes it outperforms Claude 3.5 Sonnet on SWE-bench Verified, GPQA, and MMMU, though exact percentages are omitted. Mapped to frontier-level 95s for coding, logic, and multimodal. Speed is reduced due to mandatory native thought reasoning.
OpenAI: gpt-oss-20b$1.6280
70
80
90
95
131K
81GPQA 71.5% and MMLU 85.3% map to Logic 80. AIME 2025 98.7 maps to Math 95. As a 21B lightweight MoE, Speed is 90. Coding inferred at 70 due to lack of explicit SWE-bench.
Tencent: Hy4 preview$52.5361
85
88
70
95
1.0M
89Lacking exact Hy4 scores, mapped as a 770B MoE flagship using cited 2026 frontier baselines: 40-55% SWE-bench Verified (Coding ~85) and 75-90% GPQA (Logic ~85). Configurable reasoning modes confirm native reasoning.
Anthropic: Claude Opus 4.5$450.0061
98
97
50
95
200K
97SWE-bench Verified at 80.9% maps to 98 coding. GPQA Diamond at 87.0% maps to 98 logic. MMMU at 80.7% yields 95 multimodal. As a heavyweight reasoning model with an effort parameter, speed is rated lower at 50.
Qwen: Qwen3.5-35B-A3B$15.6066
85
90
90
95
262K
90SWE-bench (69.2%) maps to 85 coding; GPQA Diamond (84.2%) maps to 88 logic. As a 35B MoE activating 3B parameters (lightweight tier), it achieves high efficiency and speed (90) while maintaining strong native reasoning capabilities.
Cohere: Command A+$27.0062
80
88
70
95
192K
88GPQA Diamond at 76% maps to 90 logic. AIME 2025 at 90% maps to 95 math. MMMU at 75.1% yields 85 multimodal. Coding inferred at 80 from Terminal-Bench (25%). Flagship MoE tier speed mapped to 70.
inclusionAI: Ling 3.1 Flash$5.2570
85
80
95
95
262K
85SWE-bench Pro (56.6%) maps to 85 coding. AIME (93.2) maps to 95 math. As a Flash-tier model, speed is heavily weighted (95), while logic and instruction are inferred lower than flagship counterparts.
OpenAI: GPT-5.6 Luna Pro$20.0066
92
93
45
95
1.1M
93Evidence lacks exact GPT-5.6 Luna Pro benchmarks. Inferred scores based on its 'Pro' heavyweight tier and native reasoning mode. Assigned high logic (95) and coding (92), with lower speed (45) typical for extended reasoning models.
Xiaomi: MiMo-V2-Flash$7.0071
92
88
90
95
262K
91SWE-bench Verified 73.4% maps to 92 coding. GPQA 83.7% maps to 90 logic. AIME 94.1% maps to 95 math. Despite the 'Flash' name, its 309B MoE architecture and native reasoning deliver flagship-level scores.

Need a shareable artifact?

Get a print-ready PDF of your results and a CSV spreadsheet. Tap the button, then enter your work email. We use it to build your files and start the download—and to email you a copy if the site owner enabled that.

AI ROI Leaderboard & Discovery by LeadsCalc

Detailed analysis

PDF Breakdown

Receive a comprehensive native vector PDF of this leaderboard: your workload, filters, top rankings, and a table snapshot (sorted: Math).

Instant setup
No CC required

By submitting, you agree to our Privacy Policy and Terms.

Agency accelerator

Whitelabel Math Leaderboard
for your site

Embed the interactive math view on your own domain — whitelabel branding, lead capture, and the same workload sliders your prospects already use on LeadsCalc.

1-Click CRM sync
Custom branding
Branded reports
Lead analytics

Free to start

$0/mo*
GET STARTED

NO CREDIT CARD REQUIRED

How it works

Methodology: How we rank Math LLMs

Transparent, benchmark-driven rankings—same craft as our single-model deep dives.

Quantitative benchmarks that drive the math axis

Our math rankings isolate performance on rigorous quantitative benchmarks like GSM8K (grade school math) and MATH (competition-level mathematics). We normalize these scores to a 0–100 axis, helping FinTech, EdTech, and data engineering teams identify models that can reliably execute complex calculations, write accurate SQL queries, and parse financial tables without silent hallucinations.

Battle Arena

Compare up to four LLMs side by side

Tick up to four models in the leaderboard table, then open Battle Arena for API pricing, benchmarks, and workload math in one view—perfect when you are shortlisting vendors for a pilot in the US, Canada, or Australia.

Prefer a head start? Jump into high-intent comparisons people search for every day—same interactive calculator, zero signup.

Open Battle ArenaUp to 4 models · Live estimates
Signals & spend

Value analysis

Benchmarks vs. estimated API cost—read the story your CFO cares about.

Using math scores without over-trusting a single number

Benchmarks orient you; they do not replace domain validation. For financial or regulated use, run your own golden tests and compliance review. Teams in Australia and Canada often add privacy constraints; US teams may require audit trails regardless of leaderboard position.

Production deployment

Quantitative Analysis & EdTech

How teams in the US, Canada, and Australia deploy these models in production.

Financial modeling, STEM tutoring, and data analytics

High math scores correlate strongly with a model's ability to write accurate SQL, parse complex financial tables, and explain STEM concepts step-by-step. FinTech companies in the US and EdTech platforms in Australia rely on these quantitatively rigorous models to power spreadsheet copilots, automated accounting audits, and personalized math tutoring applications.

Architecture

Optimizing Quantitative Accuracy

Strategies to reduce monthly API spend without sacrificing capability.

Zero-shot vs few-shot cost trade-offs

While frontier reasoning models excel at zero-shot math, they are expensive. A highly optimized architecture often uses a cheaper model provided with extensive few-shot examples and a strict system prompt. Use this leaderboard to compare the cost of a premium model against a cheaper model that might require 2,000 extra input tokens of few-shot prompting to achieve the same accuracy.

Embed-ready

Need this live Math data on your website?

Join 500+ agencies in the US and Australia using LeadsCalc to capture high-intent leads. Embed this interactive Math leaderboard on your site in about a minute—Canadian teams use the same flows for CAD-priced proposals and compliance-friendly landing pages.

Customize & Embed this ToolWhite-label · No code required
United StatesCanadaAustralia
Live preview

Your visitors compare Math models without leaving your domain.

Support & clarity

Frequently Asked Questions

Focused on teams in the United States, Canada, and Australia.

Models that score highly on the MATH benchmark generally excel at structured data tasks like SQL generation and financial analysis. However, for enterprise deployments in the US, Canada, or Australia, you should pair these models with strict system prompts and few-shot examples to guarantee consistent output formatting.