Muse Spark 1.3
Meta·
Overview
Fourth Muse Spark release in five months, live at launch in Muse Code and the Meta Model API. Meta frames the update as an efficiency change as much as a capability one: for the same agentic work it reports about 20% fewer tool calls and about 25% fewer tokens, with fewer turns and less verbose output. 1M-token context, multimodal input; xhigh reasoning effort is the generally available tier, a max tier is in limited preview for Meta partners. Vendor-reported (Meta launch scorecard, September 2026): Terminal-Bench 2.1 88.8, DeepSWE v1.1 75.4, SWEAtlas CodeBase QnA 59.4, MRCR 256K-512K 98.5 and MRCR 512K-1M 98.1. API pricing unchanged from 1.1 and 1.2 at $1.25 / $4.25 per million input/output tokens with cached input at $0.15; the contributor tier (over 90% discount in exchange for training on prompts and completions) continues.
Capabilities and innovations
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 94% | third party GPQA Diamond 94% at xhigh (max: also 94%), measured by Artificial Analysis. The article rounds to whole percent, so no decimal is recorded here - the value is deliberately less precise than the 1.2 entry's 90,4%, which came from AA's model page. Meta reports no GPQA value for 1.3. |
| Humanity’s Last Exam (no tools) | 47% | third party HLE 47% no-tools at xhigh (max: 49%), measured by Artificial Analysis, again rounded to whole percent. Caveat: the same table lists 1.2 at 45% while this dataset carries 43,9 from AA's 1.2 model page - more than rounding explains. AA now scores under Intelligence Index v4.1.1 (the 1.2 value was taken under v4.1), so the 1.2 column in that article is most likely a re-run. Flagged rather than reconciled; both entries keep the figure from the source they were taken from. |
| Terminal-Bench 2.x | 72.28% | independent Terminal-Bench 2.1 72.28%, measured by Vals AI with the Terminus 2 harness (accessed 2026-09-23). Vals AI is the reference harness for this field so values compare across vendors; vendor and other third-party figures stay in the notes below. Standard (xhigh) tier; Muse Spark 1.3 Max scores 79.03 on the same harness. Replaces 88.8 (vendor / third_party). |
| DeepSWE v1.1 | 75.4% | vendor DeepSWE v1.1 75.4 from Meta's launch scorecard for Muse Spark 1.3. Vendor self-report over its own model; the scorecard names no harness, and DeepSWE itself scores under a fixed mini-swe-agent harness. The same scorecard restates Muse Spark 1.2 at 55.0, while Meta's own August scorecard reported 59.3 for that model — see the deepswe_v1_1 entry on Muse Spark 1.2. The 1.3 figure is therefore recorded, but the 1.2-to-1.3 delta is not a like-for-like measurement. Datacurve's own DeepSWE board was not reachable from this environment, so the value is not cross-checked against it. |
- SWE-bench Pro: independent evaluation pending — Meta again reports DeepSWE v1.1 (75,4%, now recorded in deepswe_v1_1) and SWEAtlas CodeBase QnA (59,4%, no field) instead of SWE-bench Pro. Same situation as for 1.2: the Scale AI SWE-bench Pro leaderboard, which supplied the 1.1 value (61,5%), carries no 1.3 entry as of 2026-09-03.
- MMLU-Pro: independent evaluation pending — Not reported by Meta, and Vals AI has no Muse Spark 1.3 run as of 2026-09-03 (its newest Muse Spark page is 1.1). The 1.2 entry has the same gap.
- MMMU-Pro: not reported by the vendor
API pricing
$1.25 per million input tokens, $4.25 per million output tokens (USD, cheapest OpenRouter endpoint, checked 2026-09-03)
Reliability
- tau3_banking
- 47 ()third party
- omniscience_index
- 25 ()independent
Links
More from Meta
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.