GSM-Infinite
Models solve generated arithmetic problems across different context lengths and numbers of reasoning steps. The benchmark varies how many irrelevant details appear alongside each problem.
On November 19, 2026, the repository listed DeepSeek-R1 first on its zero-noise table with an average of 8534.88. GPT-o3-mini scored 6931.88.
- Made by
- Carnegie Mellon University and Meta AI
- Released
- February 2025
- Kind
- Reasoning over long documents
- Level
- School
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
DeepSeek-R1 May 2025 #122 on the capability index
- Last model added
- May 2025
- Scores refreshed
- November 20th, 2026
DeepSeek-R1 leads with 8534.9 among models released by May 2025 DeepSeek-R1 leads with 8534.9 among models released by May 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in May 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 8534.9
DeepSeek-R1
- 6931.9 o3-mini
- 4951.1 o1-mini
- 3606.2
DeepSeek-V3
- 2860.7
QwQ-32B-Preview
- 2841.6
Gemini 1.5 Pro
- 2519.5 Claude 3.5 Sonnet
- 2507.6 mistral-large-2411
- 2187.1
Qwen2.5-72B
- 2096.0 GPT-4o
- 1574.3
Gemini 1.5 Flash
- 1541.5 llama-3.1-70b-instruct
- 1503.2
MiniMax-Text-01
- 1276.2 llama-3.1-405b-instruct
- 1236.5 GPT-4o mini
- 911.5 Claude 3.5 Haiku
- 764.1 qwen-2.5-7b-instruct
- 618.3 llama-3.1-8b-instruct
- 602.5 Jamba 1.5 Large
- 1
DeepSeek-R1 May 2025, Zero Noise 8534.9
- 2 o3-mini Zero Noise 6931.9
- 3 o1-mini Zero Noise 4951.1
- 4
DeepSeek-V3 Mar 2025, Zero Noise 3606.2
- 5
QwQ-32B-Preview Zero Noise 2860.7
- 6
Gemini 1.5 Pro Sep 2024, Zero Noise 2841.6
- 7 Claude 3.5 Sonnet Zero Noise 2519.5
- 8 mistral-large-2411 Zero Noise 2507.6
- 9
Qwen2.5-72B Zero Noise 2187.1
- 10 GPT-4o Nov 2024, Zero Noise 2096.0
- 11
Gemini 1.5 Flash Sep 2024, Zero Noise 1574.3
- 12 llama-3.1-70b-instruct Zero Noise 1541.5
- 13
MiniMax-Text-01 Zero Noise 1503.2
- 14 llama-3.1-405b-instruct Zero Noise 1276.2
- 15 GPT-4o mini Zero Noise 1236.5
- 16 Claude 3.5 Haiku Zero Noise 911.5
- 17 qwen-2.5-7b-instruct Zero Noise 764.1
- 18 llama-3.1-8b-instruct Zero Noise 618.3
- 19 Jamba 1.5 Large Zero Noise 602.5
Source: Official GSM-Infinite leaderboard
- 1
DeepSeek-R1 May 2025, Zero Noise 8534.9
- 2 o3-mini Zero Noise 6931.9
- 3 o1-mini Zero Noise 4951.1
- 4
DeepSeek-V3 Mar 2025, Zero Noise 3606.2
- 5
QwQ-32B-Preview Zero Noise 2860.7
- 6
Gemini 1.5 Pro Sep 2024, Zero Noise 2841.6
- 7 Claude 3.5 Sonnet Zero Noise 2519.5
- 8
Qwen2.5-72B Zero Noise 2187.1
- 9 GPT-4o Nov 2024, Zero Noise 2096.0
- 10
Gemini 1.5 Flash Sep 2024, Zero Noise 1574.3
- 11
MiniMax-Text-01 Zero Noise 1503.2
- 12 GPT-4o mini Zero Noise 1236.5
- 13 Claude 3.5 Haiku Zero Noise 911.5
- 14 Jamba 1.5 Large Zero Noise 602.5
Source: Official GSM-Infinite leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 8534.9 | Zero Noise | May 2025 | Official leaderboard |
| 2 | o3-mini | 6931.9 | Zero Noise | Jan 2025 | Official leaderboard |
| 3 | o1-mini | 4951.1 | Zero Noise | Sep 2024 | Official leaderboard |
| 4 | | 3606.2 | Zero Noise | Mar 2025 | Official leaderboard |
| 5 | | 2860.7 | Zero Noise | Nov 2024 | Official leaderboard |
| 6 | | 2841.6 | Zero Noise | Sep 2024 | Official leaderboard |
| 7 | Claude 3.5 Sonnet | 2519.5 | Zero Noise | Jun 2024 | Official leaderboard |
| 8 | mistral-large-2411 | 2507.6 | Zero Noise | Official leaderboard | |
| 9 | | 2187.1 | Zero Noise | Sep 2024 | Official leaderboard |
| 10 | GPT-4o Nov 2024 | 2096.0 | Zero Noise | Nov 2024 | Official leaderboard |
| 11 | | 1574.3 | Zero Noise | Aug 2024 | Official leaderboard |
| 12 | llama-3.1-70b-instruct | 1541.5 | Zero Noise | Official leaderboard | |
| 13 | | 1503.2 | Zero Noise | Jan 2025 | Official leaderboard |
| 14 | llama-3.1-405b-instruct | 1276.2 | Zero Noise | Official leaderboard | |
| 15 | GPT-4o mini | 1236.5 | Zero Noise | Jul 2024 | Official leaderboard |
| 16 | Claude 3.5 Haiku | 911.5 | Zero Noise | Oct 2024 | Official leaderboard |
| 17 | qwen-2.5-7b-instruct | 764.1 | Zero Noise | Official leaderboard | |
| 18 | llama-3.1-8b-instruct | 618.3 | Zero Noise | Official leaderboard | |
| 19 | Jamba 1.5 Large | 602.5 | Zero Noise | Aug 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 8534.9 | Zero Noise | May 2025 | Official leaderboard |
| 2 | o3-mini | 6931.9 | Zero Noise | Jan 2025 | Official leaderboard |
| 3 | o1-mini | 4951.1 | Zero Noise | Sep 2024 | Official leaderboard |
| 4 | | 3606.2 | Zero Noise | Mar 2025 | Official leaderboard |
| 5 | | 2860.7 | Zero Noise | Nov 2024 | Official leaderboard |
| 6 | | 2841.6 | Zero Noise | Sep 2024 | Official leaderboard |
| 7 | Claude 3.5 Sonnet | 2519.5 | Zero Noise | Jun 2024 | Official leaderboard |
| 8 | | 2187.1 | Zero Noise | Sep 2024 | Official leaderboard |
| 9 | GPT-4o Nov 2024 | 2096.0 | Zero Noise | Nov 2024 | Official leaderboard |
| 10 | | 1574.3 | Zero Noise | Aug 2024 | Official leaderboard |
| 11 | | 1503.2 | Zero Noise | Jan 2025 | Official leaderboard |
| 12 | GPT-4o mini | 1236.5 | Zero Noise | Jul 2024 | Official leaderboard |
| 13 | Claude 3.5 Haiku | 911.5 | Zero Noise | Oct 2024 | Official leaderboard |
| 14 | Jamba 1.5 Large | 602.5 | Zero Noise | Aug 2024 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Symbolic, Medium and Hard. DeepSeek-R1 leads 3 of them, and Gemini 1.5 Pro leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.
Symbolic
14 models we track have a score here.
- 1
DeepSeek-R1 May 2025 7280.0
- 2 o3-mini 6690.0
- 3 o1-mini 5060.0
- 4
DeepSeek-V3 Mar 2025 4310.0
- 5
QwQ-32B-Preview 3530.0
- 6
Gemini 1.5 Pro Sep 2024 2547.0
- 7 GPT-4o Nov 2024 ↑2 2379.0
- 8 Claude 3.5 Sonnet ↓1 2161.0
- 9
Qwen2.5-72B ↓1 2048.0
- 10
Gemini 1.5 Flash Sep 2024 1970.0
Medium
14 models we track have a score here.
- 1
DeepSeek-R1 May 2025 9750.9
- 2 o3-mini 8335.7
- 3 o1-mini 6054.9
- 4
DeepSeek-V3 Mar 2025 4100.8
- 5
Gemini 1.5 Pro Sep 2024 ↑1 3659.6
- 6 Claude 3.5 Sonnet ↑1 3281.8
- 7
QwQ-32B-Preview ↓2 3205.8
- 8
Qwen2.5-72B 2496.8
- 9 GPT-4o Nov 2024 2457.4
- 10
MiniMax-Text-01 ↑1 1712.6
Hard
14 models we track have a score here.
- 1
DeepSeek-R1 May 2025 8573.8
- 2 o3-mini 5770.0
- 3 o1-mini 3738.4
- 4
DeepSeek-V3 Mar 2025 2407.9
- 5
Gemini 1.5 Pro Sep 2024 ↑1 2318.3
- 6 Claude 3.5 Sonnet ↑1 2115.8
- 7
Qwen2.5-72B ↑1 2016.4
- 8
QwQ-32B-Preview ↓3 1846.2
- 9 GPT-4o Nov 2024 1451.5
- 10
Gemini 1.5 Flash Sep 2024 1274.3
8K
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑5 1182.4
- 2
DeepSeek-V3 Mar 2025 ↑2 935.1
- 3
Qwen2.5-72B ↑5 927.3
- 4
Gemini 1.5 Flash Sep 2024 ↑6 673.9
- 5
MiniMax-Text-01 ↑6 481.3
- 6 GPT-4o mini ↑6 401.0
16K
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑5 896.3
- 2
Qwen2.5-72B ↑6 681.5
- 3
DeepSeek-V3 Mar 2025 ↑1 477.0
- 4
Gemini 1.5 Flash Sep 2024 ↑6 476.7
- 5
MiniMax-Text-01 ↑6 359.6
- 6 GPT-4o mini ↑6 337.8
32K
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑5 813.0
- 2
Qwen2.5-72B ↑6 563.6
- 3
Gemini 1.5 Flash Sep 2024 ↑7 377.4
- 4
MiniMax-Text-01 ↑7 325.9
- 5
DeepSeek-V3 Mar 2025 ↓1 313.7
- 6 GPT-4o mini ↑6 275.6
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official GSM-Infinite leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Zero Noise | 8534.9 | ||||
| o3-mini | Zero Noise | 6931.9 | |||
| o1-mini | Zero Noise | 4951.1 | |||
| Zero Noise | 3606.2 | ||||
| Zero Noise | 2860.7 | ||||
| Zero Noise | 2841.6 | ||||
| Claude 3.5 Sonnet | Zero Noise | 2519.5 | |||
| Zero Noise | 2187.1 | ||||
| GPT-4o Nov 2024 | Zero Noise | 2096.0 | |||
| Zero Noise | 1574.3 | ||||
| Zero Noise | 1503.2 | ||||
| GPT-4o mini | Zero Noise | 1236.5 | |||
| Long Context | 963.9 | ||||
| Claude 3.5 Haiku | Zero Noise | 911.5 | |||
| Long Context | 724.2 | ||||
| Jamba 1.5 Large | Zero Noise | 602.5 | |||
| Long Context | 575.2 | ||||
| Long Context | 509.3 | ||||
| Long Context | 388.9 | ||||
| GPT-4o mini | Long Context | 338.1 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official GSM-Infinite leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Zero Noise | 8534.9 | ||||
| o3-mini | Zero Noise | 6931.9 | |||
| o1-mini | Zero Noise | 4951.1 | |||
| Zero Noise | 3606.2 | ||||
| Zero Noise | 2860.7 | ||||
| Zero Noise | 2841.6 | ||||
| Claude 3.5 Sonnet | Zero Noise | 2519.5 | |||
| Zero Noise | 2187.1 | ||||
| GPT-4o Nov 2024 | Zero Noise | 2096.0 | |||
| Zero Noise | 1574.3 | ||||
| Zero Noise | 1503.2 | ||||
| GPT-4o mini | Zero Noise | 1236.5 | |||
| Long Context | 963.9 | ||||
| Claude 3.5 Haiku | Zero Noise | 911.5 | |||
| Long Context | 724.2 | ||||
| Jamba 1.5 Large | Zero Noise | 602.5 | |||
| Long Context | 575.2 | ||||
| Long Context | 509.3 | ||||
| Long Context | 388.9 | ||||
| GPT-4o mini | Long Context | 338.1 |
2 models have held number one on the official leaderboard since its release in February 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official GSM-Infinite leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official GSM-Infinite leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Long context
- MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens.
Muse Spark 1.3 98.5%
- LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy.
Inkling 2 Small 70.6%
- GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
- OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin.
Gemini 3.7 Flash 89%
- CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
- AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key.
Step 5 Preview 88.3%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 18 months ago, in May 2025, for DeepSeek-R1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (19 entries).
- Pass Models scored 14 models we track, plus 5 other entries on its leaderboard.
- Warning Newest score The newest came 18 months ago, in May 2025, for DeepSeek-R1.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-R1 (#122).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on infiniailab-gsm-infinite-leaderboard.hf.space: 20 rows for models we track and 5 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.