GLM-5.1: benchmark scores, price and ranking

GLM-5.1 from Z.ai (Zhipu AI) ranks #246 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.6), based on 18 benchmark results captured up to 2026-10-13.

Organisation

Z.ai (Zhipu AI)

Type

Open-weight / local model

Open weights

Yes

Released

2026-04-07 (source: epoch)

Cheapest API price

$0.966 in / $3.04 out per million tokens (via openrouter, observed 2026-10-13T19:47Z)

Aggregate rank

#246 of 743 (score 49.6)

Relative to other models, GLM-5.1 is strongest on Epoch ECI (#10 of 204) and weakest on APEX-Agents (#11 of 16).

Across the 16 benchmarks where at least ten models are scored, GLM-5.1 is in the top 10% on 1 and in the top half on 12.

Its cheapest listed input price, $0.966 per million tokens, is lower than that of 37% of the 427 models with a listed price.

GLM-5.1 benchmark results

About GLM-5.1

GLM-5.1 is an open-weight model that can run on your own hardware from Z.ai (Zhipu AI). It was released on 2026-04-07, according to Epoch AI. The cheapest API listing we track charges $0.966 per million input tokens and $3.04 per million output tokens, through openrouter. We hold 18 benchmark results for it across 4 areas, and 1 is in the top tenth of its board.

Where GLM-5.1 stands

On our aggregate score, GLM-5.1 is #246 of 743 ranked models, around the middle of the table. Its score is 49.6; the scale is centred on 50, so it sits 0.4 points below the typical model. That beats 67% of the ranked field. Among the 6 ranked Z.ai (Zhipu AI) models it is #3. The next one up is GLM-5 at 51.5. The next one down is GLM-5.3-Flash (max) at 49.6.

GLM-5.1, benchmark by benchmark

On Epoch ECI, GLM-5.1 scores 150 and ranks #10 of 204. Only 9 models score higher, led by Qwen 3.8 Max at 156, which is 7 points ahead. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GLM-5.1 is 23 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On Vending-Bench 2, GLM-5.1 reaches $5,634. It ranks #2 of 19, ahead of 89% of the field, and 570 points behind Kimi K2.6 at $6,205. The results either side are Kimi K2.6 ($6,205) and Gemini 3 Pro Preview ($5,478). It covers running a vending business for a year (final money, $). The board median is $2,377, so GLM-5.1 is 3,258 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 manages 74.2% on SWE-bench Verified, good for #11 of 73. Claude Opus 4.7 (max) leads at 83.5%, 9.3 points further up, and 85% of models sit below. The results either side are Gemini 3 Pro Preview (74.2%) and GPT-5 (high) (73.6%). It covers real GitHub issues resolved. The board median is 56.4%, so GLM-5.1 is 17.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

OTIS Mock AIME puts GLM-5.1 at 93.3%, #31 of 189. That beats 84% of the models tested, but 6.7 points short of Claude Fable 5.1 (max) (100.0%). The results either side are GLM-5.3-Flash (max) (93.9%) and grok-4.3 (high) (93.3%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so GLM-5.1 is 35.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On WeirdML, GLM-5.1 reaches 57.1%. It ranks #20 of 109, ahead of 82% of the field, and 36.2 points behind GPT-6 Astra (max) at 93.3%. The results either side are Muse Spark 1.2 (xhigh) (60.3%) and Kimi K2.6 (55.9%). It covers unusual machine-learning tasks. The board median is 41.2%, so GLM-5.1 is 15.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 manages 55.1% on SimpleBench, good for #15 of 61. Claude Fable 5 (max) leads at 81.9%, 26.8 points further up, and 75% of models sit below. The results either side are grok-4-1-fast-reasoning (56.0%) and GLM-5 (53.2%). It covers trick questions that test common sense. The board median is 41.4%, so GLM-5.1 is 13.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 lands below the middle on SciCode: 43.8%, #54 of 106, with 50% of the field scoring higher. Claude Opus 5.5 (max) leads at 66.9%; the closest result above is Muse Glimmer (high) at 44.9%. It covers scientific research code. The board median is 44.3%, so GLM-5.1 is 0.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 lands below the middle on SimpleQA Verified: 34.0%, #43 of 69, with 61% of the field scoring higher. gemini-4-argon-high leads at 76.0%; the closest result above is Kimi K2.5 at 34.3%. It covers short factual questions. The board median is 41.0%, so GLM-5.1 is 7.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 lands below the middle on FrontierMath T1-3: 36.8%, #45 of 68, with 65% of the field scoring higher. GPT-6 Astra (max) leads at 93.7%; the closest result above is Qwen 3.6 Plus (2026-04-02) at 38.2%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so GLM-5.1 is 18.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GLM-5.1 lands below the middle on APEX-Agents: 40.9%, #11 of 16, with 62% of the field scoring higher. Claude Sonnet 5.5 (max) leads at 75.5%; the closest result above is GPT-6 Luna (max) at 44.3%. It covers long professional agent tasks. The board median is 47.8%, so GLM-5.1 is 6.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 8 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Software engineering: solid, ahead of 65% of the field on average across 4 benchmarks. Its best board here is SWE-bench Verified (#11 of 73) and its weakest is SciCode (#54 of 106). Reasoning, maths and science: solid, ahead of 63% of the field on average across 6 benchmarks. Its best board here is OTIS Mock AIME (#31 of 189) and its weakest is FrontierMath T1-3 (#45 of 68). General knowledge and chat: solid, ahead of 73% of the field on average across 5 benchmarks. Its best board here is Epoch ECI (#10 of 204) and its weakest is SimpleQA Verified (#43 of 69).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so GLM-5.1 costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen3.7 Flash ($0.030, 50.5). Similar scores cost more on claude-3-5-haiku-20241022 ($1.00) and nousresearch/hermes-3-llama-3.1-405b ($1.00).

Release history

The Z.ai (Zhipu AI) model released before it was GLM-5 on 2026-02-12, which scores 51.5. The next one was GLM-5.3 (max) on 2026-08-14, at 53.8.

Reading these numbers

The 18 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (17), HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 1 other reasoning-effort setting of this model, which redirect here. This page shows the highest.

GLM-5.1 is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

• #243 Qwen3-235B-A22B-Thinking-2507 (49.7)
• #244 Inkling Small (xhigh) (49.7)
• #245 GLM-4.5-FP8 (49.6)
• #247 Opus 4.5 (Thinking, 64K) (49.6)
• #248 GLM-5.3-Flash (max) (49.6)
• #249 grok-4.20-0309-reasoning (49.6)

More from Z.ai (Zhipu AI)

• GLM-5.3 (max) (#28, 53.8)
• GLM-5 (#118, 51.5)
• GLM-5.3-Flash (max) (#248, 49.6)
• GLM-4.7 (Novita) (#355, 48.4)
• GLM-4.7 (#410, 47.7)

Compare it on the live leaderboard → · How the aggregate score works