Across 19 comparable benchmarks, Inkling 2 Mini has better reported results on 19 and worse on 0. 1 further shared result is listed below, each with the reason it is not counted.
Strong evidence19 of 20 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Inkling 2 Mini | Muse Glimmer-30B |
|---|---|---|
| Context window | 1M tokens | 128K tokens |
| Input / 1M | $0.150 | $0.300 |
| Output / 1M | $0.500 | $1.20 |
| Blended (4:1) | $0.123 | $0.293 |
| Status | Available | Available |
| Released | November 20, 2026 | August 10, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 12 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Inkling 2 Mini ahead on 2 of 2 counted
Inkling 2 Mini ahead on 3 of 3 counted
Inkling 2 Mini ahead on 2 of 2 counted
Inkling 2 Mini ahead on 1 of 1 counted
Inkling 2 Mini ahead on 6 of 6 counted
Inkling 2 Mini ahead on 3 of 3 counted
No shared comparable results for Abstract reasoning, Mathematics, Science & health, Cybersecurity.
Published scores, with matching modes where available. Gaps show Inkling 2 Mini relative to Muse Glimmer-30B. Reading the results
| Benchmark | Inkling 2 Mini | Muse Glimmer-30B | Gap |
|---|---|---|---|
| DeepSWERepository Engineering · Pass@1 (DeepSWE v1.1) | 48.2Thinking · tools | 4.4Thinking · tools | +43.8 pts#61 vs #72 of 73 |
| FrontierCode 2.0Repository Engineering · Weighted rubric score | 15.1Thinking · tools | 1.5Thinking · tools | 10.1×#26 vs #35 of 36 |
| AutomationBench-AATool Orchestration · Guardrail-safe objective completion rate | 41.8Thinking · tools | 6.8Thinking · tools | +35.0 pts#17 vs #18 of 18 |
| MCP-AtlasTool Orchestration · Pass rate / claim coverage | 82.7Thinking · tools | 75.5≠Thinking High · tools | +7.2 pts#14 vs #31 of 55 |
| ScreenSpot-Pro (no tools)GUI Grounding · Success rate (%) | 76.5Thinking · no tools | 75.4Thinking · no tools | +1.1 pts#4 vs #5 of 8 |
| BrowseCompFact Finding · Accuracy | 79.0Thinking · tools | 63.9Thinking · tools | +15.1 pts#24 vs #39 of 61 |
| DeepSearchQAFact Finding · F1 score | 85.3Thinking · tools | 74.6≠Thinking High · tools + web | 1.14×#4 vs #8 of 9 |
| LongBench v2Long Reasoning · Accuracy | 66.9Thinking · no tools | 33.1Thinking · no tools | +33.8 pts#2 vs #22 of 22 |
| ChartographyDocuments & Charts · Score | 72.5Thinking · tools | 25.1Thinking · tools | 2.89×#16 vs #28 of 29 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 16.8Thinking · no tools | 11.8Thinking · no tools | +5.0 pts#38 vs #54 of 96 |
| MMMU-ProVisual Understanding · Accuracy | 74.9Thinking · no tools | 74.0≠Thinking High · no tools | +0.9 pts#69 vs #72 of 136 |
| OmniDocBenchDocuments & Charts · Accuracy | 92.8Thinking · no tools | 75.8≠Thinking High · no tools | +17.0 pts#1 vs #6 of 6 |
| PerceptionBenchVisual Understanding · Accuracy | 57.5Thinking · no tools | 42.8Thinking · no tools | +14.7 pts#11 vs #17 of 19 |
| ZeroBench MainVisual Understanding · Pass@1 / Pass@5 / Pass^5 | 34.0Thinking · tools | 17.0Thinking · tools | +17.0 pts#16 vs #18 of 21 |
| AA-AnalystAgentData Analysis · pass^5 (%) | 46.3Thinking · tools | 20.0Thinking · tools | +26.3 pts#16 vs #28 of 39 |
| AA-BriefcaseOffice & Business · AA-Briefcase Elo | 1263Thinking · tools | 478Thinking · tools | 2.64×#18 vs #20 of 20 |
| GDPval-AA v2Cross-industry Work · Elo score | 1319Thinking · tools | 953≠Thinking High · tools | 1.38×#19 vs #21 of 23 |
| JobBenchCross-industry Work · Mean task reward (%)Not counted · This metric has no better direction | 49.6Thinking · tools | 16.1Thinking · tools | — |
| HLE-DiamondKnowledge Exams · Accuracy (%) | 15.2Thinking · no tools | 9.1Thinking · no tools | +6.1 pts#13 vs #14 of 16 |
| AA Intelligence Index v5.0.1Capability Indices · Index (0-100) | 20.1Thinking · no tools | 6.3≠Thinking High · tools | 3.17×#44 vs #55 of 62 |
Repository Engineering · Pass@1 (DeepSWE v1.1)
Repository Engineering · Weighted rubric score
Tool Orchestration · Guardrail-safe objective completion rate
Tool Orchestration · Pass rate / claim coverage
GUI Grounding · Success rate (%)
Fact Finding · Accuracy
Fact Finding · F1 score
Long Reasoning · Accuracy
Documents & Charts · Score
Documents & Charts · Task pass rate (%)
Visual Understanding · Accuracy
Documents & Charts · Accuracy
Visual Understanding · Accuracy
Visual Understanding · Pass@1 / Pass@5 / Pass^5
Data Analysis · pass^5 (%)
Office & Business · AA-Briefcase Elo
Cross-industry Work · Elo score
Cross-industry Work · Mean task reward (%)
Not counted · This metric has no better direction
Knowledge Exams · Accuracy (%)
Capability Indices · Index (0-100)
A dash means no result is available.
| Benchmark | Inkling 2 Mini | Muse Glimmer-30B |
|---|---|---|
| AIME 2026 | — | 94.7 |
| GPQA Diamond | — | 83.5 |
| HLE | — | 22.0 |
| Riemann-bench | — | 13.6 |
| SciCode | — | 43.6 |
| SWE-Bench Pro - Public | — | 51.2 |
| SWE-bench Verified | — | 76.0 |
| Terminal-Bench 2.1 | — | 51.7 |
| Vibe Code Bench v1.1 | 77.9 | — |
| OSWorld-Verified | — | 65.9 |
| Vals Index v2.2 | 46.5 | — |
| Creative Writing | — | 1804 |
| IF Bench | — | 77.0 |
| AA-LCR | — | 80.0 |
| OpenAI MRCR v2 (8-needle, 256K–512K) | 46.4 | — |
| CharXiv RQ | — | 78.8 |
| τ³-Banking | — | 23.5 |
| ARC-AGI-1 | 84.5 | — |
| ARC-AGI-2 | 49.3 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Inkling 2 Mini costs58%lessthan Muse Glimmer-30B per million tokens — 2.4× cheaper.Using standard rates at this token mix.
Inkling 2 Mini: Standard pricing. Tinker 64K/256K training (1M sampling); fine-tuning billed separately ($0.75/1M for 64K, $1.50/1M for 256K).
Muse Glimmer-30B: Standard pricing. DeepInfra official models API (meta-models/Muse-Glimmer-30B) verified 2026-11-13
| Price / 1M tokens | Inkling 2 Mini | Muse Glimmer-30B | Ratio |
|---|---|---|---|
| Input | $0.15 | $0.30 | 0.50× |
| Output | $0.50 | $1.20 | 0.42× |
| Cached input | $0.015 | $0.04 | 0.38× |
| Cache write | — | — | — |
| Blended | $0.123 | $0.293 | 0.42× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Inkling 2 Mini | Muse Glimmer-30B |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported |
| Attribute | Inkling 2 Mini | Muse Glimmer-30B |
|---|---|---|
| Availability | Available | Available |
| Provider | Thinking Machines Lab | Facebook AI Research Lab |
| Model type | Reasoning model | Reasoning model |
| First release | November 20, 2026 | August 10, 2026 |
| Context window | 1M tokens | 128K tokens |
| Total parameters | 26.4B | 29.6B |
| Active parameters | 5.4B | 29.6B |
| Architecture | Mixture of Experts (MoE) | Dense |
| Documented capabilities | Reasoning, Coding, Tool use, Long context | Reasoning, Coding, Function calling, Tool use, Structured output, Computer use, Web search, Long context |
| Knowledge cutoff | — | 2026-01-04 |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | Apache 2.0 | Apache 2.0 |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Inkling 2 Mini or Muse Glimmer-30B? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.